Methods and systems for irrigation guidance
11291172 · 2022-04-05
Assignee
Inventors
Cpc classification
B64U2101/30
PERFORMING OPERATIONS; TRANSPORTING
A01G25/167
HUMAN NECESSITIES
Y02A40/10
GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
Y02A40/22
GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
A01G25/165
HUMAN NECESSITIES
International classification
B64G1/10
PERFORMING OPERATIONS; TRANSPORTING
Abstract
The present invention provides systems and methods in the field of precision agriculture, particularly to systems and methods for precision irrigation that is based, among other factors, upon actual and forecasted water needs of a crop.
Claims
1. A method for managing agricultural irrigation of a crop in an area of a field or a subplot thereof during a growing period, the method comprising: receiving data indicative of an irrigation recommendation function of the crop during a growing period (IR(t)), data indicative of a current crop water potential at a time t.sub.S within the growing period, data indicative of an evapotranspiration (ET0) at t.sub.S, data indicative of a last irrigation time and data indicative of a crop coefficient Kc; computing a current water stress coefficient Ks.sup.cur(t.sub.S); computing an actual evapotranspiration (ETa) at t.sub.S (ETa(t.sub.S)) of said crop by taking a product of Ks.sup.cur(t.sub.S) and a corresponding non-stress crop evapotranspiration (ETc) at t.sub.S (ETc(t.sub.S)), wherein ETc(t.sub.S)=ET0(t.sub.S)*Kc(t.sub.S); and if ETa(t.sub.S)≥IR(t.sub.S), setting an optimal irrigation time (t.sub.opt) by: extrapolating a line L passing through or near a first point P.sub.1 and a second point P.sub.2, P.sub.1 defined by first coordinates (t.sub.L, ETc(t.sub.L)) comprising a last irrigation time t.sub.L, which is earlier than t.sub.S, and ETc at t.sub.L, and P.sub.2 defined by second coordinates (t.sub.S, ETa(t.sub.S)); obtaining a third point P.sub.3, whereat line L intersects, or is tangent to, a curve defined by IR(t), wherein t.sub.opt is equal to the day of the time coordinate of P.sub.3; and setting a forecast irrigation amount (FIA) by: computing a value v indicative of an integral of IR(t), between t.sub.L+1 and t.sub.opt, wherein t.sub.L+1 equals t.sub.L plus one day, wherein the FIA is equal to v.
2. The method of claim 1, wherein said method is carried out within a computing environment comprising at least one computer processor and at least one computer-readable non-transitory storage medium operably coupled to the computer processor and having program instructions stored therein and data specifying a crop type, a boundary of the field area, a start of the growing period, and optionally values of a crop coefficient Kc for the growing period, the computer processor being operable to execute the program instructions to generate an irrigation plan comprising the optimal irrigation time (t.sub.opt) for a next irrigation and the forecast irrigation amount (FIA) at t.sub.opt; and/or further comprising generating, as output data, the optimal irrigation time (t.sub.opt) and the forecast irrigation amount (FIA).
3. The method of claim 1, wherein the method further comprises, if ETa(t.sub.S)<IR(t.sub.S): setting t.sub.opt equal to t.sub.S; setting a compensating forecast irrigation amount (cFIA) by: computing a value u.sub.1 indicative of an integral of IR(t) between t.sub.L+1 and t.sub.S; computing a value u.sub.2 indicative of an area S defined by the points P.sub.1 and P.sub.2 and a fourth point P.sub.4=(t.sub.S, IR(t.sub.S)), wherein the cFIA is equal to u.sub.1+u.sub.2; and generating, as output data, t.sub.opt and the cFIA; and/or further comprising setting a next irrigation time t.sub.N equal to t.sub.opt.
4. The method of claim 1, wherein a next irrigation time t.sub.N is predetermined, the method further comprising for ETa(t.sub.S)≥IR(t.sub.S): if t.sub.N=t.sub.opt, generating, as output data, the forecast irrigation amount (FIA); and if t.sub.N≠t.sub.opt, obtaining an adjusted FIA (aFIA) by: computing a second value v.sub.2 indicative of an area A defined by the points P.sub.1, P.sub.3, and a point P.sub.5=(t.sub.N, IR(t.sub.N)); if t.sub.N<t.sub.opt: setting the aFIA to equal FIA+v.sub.2; and if t.sub.N>t.sub.opt: setting the aFIA to equal FIA−v.sub.2; and generating, as output data, the aFIA.
5. The method of claim 4, further comprising for ETa(t.sub.S)<IR(t.sub.S): extrapolating the line L; obtaining the point P.sub.5 and a point P.sub.6 defined by coordinates (t.sub.N, L(t.sub.N)); and setting a compensating forecast irrigation amount (cFIA) by: computing a value w.sub.1 indicative of an integral of IR(t) between t.sub.L+1 and t.sub.N; computing a value w.sub.2 indicative of an area R defined by the points P.sub.1, P.sub.5, and P.sub.6, wherein the cFIA is equal to w.sub.1+w.sub.2; and generating, as output data, the cFIA.
6. The method of claim 1, further comprising outputting an alert when ETa(t.sub.S)<IR(t.sub.S); and/or obtaining Ks.sup.cur(t.sub.S) by computing a value indicative of a ratio of a first difference to a second difference; wherein the first difference is defined as a difference between a non-stress water potential taken at t.sub.S from a non-stress reference index of the crop, and the current crop water potential at t.sub.S; and wherein the second difference is defined as a difference between the non-stress water potential and a maximum stress water potential taken at t.sub.S from a maximum stress reference index of said crop.
7. The method of claim 1, wherein the field area comprises a plurality of subplots, said method comprises generating a set of irrigation plans, each plan comprising a subplot specific optimal irrigation time and a corresponding forecast irrigation amount; wherein Ks.sup.cur(t.sub.S), ETa(t.sub.S), t.sub.opt, the FIA are permanently stored in the at least one non-transitory computer-readable storage medium, in a section thereof dedicated to the field; wherein the current water potential is obtained using remote sensing data and/or in-situ measurement data; and/or wherein remote sensing data are thermal data or microwave data of the field soil.
8. The method of claim 7, wherein the remote sensing data comprises images from one or more satellites, one or more drones, one or more airplanes, or a combination thereof; and/or wherein the remote sensing data are spectral reflectance data, thermal data, radar data of the crop canopy, or a combination thereof.
9. The method of claim 8, wherein each pixel or a plurality of pixels in each of the images contains data corresponding to a respective area within the field or the subplot; and/or further comprising obtaining one or more remote sensing derived indices using the spectral reflectance data, thermal data, and/or radar data of the crop canopy.
10. The method of claim 9, wherein the one or more remote sensing derived indices comprise at least one of the normalized difference water index (NDWI), derived from spectral reflectance data in the visible, near infrared (NIR) and short wave infrared (SWIR) spectral bands, and the crop water stress index (CWSI), derived from crop and air temperature measurement data; or the remote sensing data are spectral reflectance data in the red and infrared spectral bands, and optionally in the blue spectral band, allowing to obtain at least one of the normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI) therefrom.
11. The method of claim 1, wherein the Kc values are adjusted based on remote sensing data obtained during the growing period and/or wherein the line L is straight.
12. The method of claim 1, further comprising, after obtaining t.sub.opt: computing a current water stress coefficient Ks.sup.cur(t′.sub.S), wherein t.sub.S<t′.sub.S<t.sub.opt; computing an actual evapotranspiration (ETa) at t′.sub.S(ETa(t′.sub.S)); and if ETa(t′.sub.S)≥IR(t′.sub.S): adjusting t.sub.opt by: extrapolating a line L′ passing through or near first point P.sub.1, second point P.sub.2, and point P′.sub.2 defined by second coordinates (t′.sub.S, ETa(t′.sub.S)); obtaining a point P′.sub.3, whereat line L′ intersects, or is tangent to, the curve defined by IR(t); and setting t.sub.opt to equal the day of the time coordinate of P′.sub.3; and adjusting the FIA by: computing a value v′ indicative of an integral of IR(t), between t.sub.L+1 and t.sub.N; and setting the FIA to equal v′; and/or wherein the line L is selected from a family of lines including curved lines.
13. The method of claim 2, wherein the output data are sent to an irrigation controller located near or within the field; and/or wherein the output data are sent to a remote device of a user, the user being in charge of the irrigation of the field.
14. A system for managing agricultural irrigation of a crop in an area of a field or a part thereof, the system comprising: a computing environment, the computing environment comprising: at least one non-transitory computer-readable storage medium having computer-executable instructions stored therein and data specifying a crop type, a boundary of the field area, a start and an end of the growing period, and values of a crop coefficient Kc for the growing period; and at least one computer processor operably coupled to the at least one computer-readable non-transitory storage medium and configured by the computer-executable instructions; wherein the computing environment is able to: receive data indicative of a current crop water potential at a time t.sub.S within the growing period, data indicative of an evapotranspiration (ET0) at t.sub.S, and data indicative of a last irrigation time; compute a current water stress coefficient Ks.sup.cur(t.sub.S); compute an actual evapotranspiration (ETa) at t.sub.S (ETa(t.sub.S)) of said crop by taking a product of Ks.sup.cur(t.sub.S) and a corresponding non-stress crop evapotranspiration (ETc) at t.sub.S (ETc(t.sub.S)), wherein ETc(t.sub.S)=ET0(t.sub.S)*Kc(t.sub.S); check whether ETa(t.sub.S)≥IR(t.sub.S), wherein IR(t) is an irrigation recommendation function of the crop; and if ETa(t.sub.S)≥IR(t.sub.S): obtain t.sub.opt by: extrapolating a line L passing through or near a first point P.sub.1 and a second point P.sub.2, P.sub.1 defined by first coordinates (t.sub.L, ETc(t.sub.L)) comprising a last irrigation time which is earlier than t.sub.S, and ETc at t.sub.L, and P.sub.2 defined by second coordinates (t.sub.S, ETa(t.sub.S)); obtaining a third point P.sub.3, whereat line L intersects, or is tangent to, a curve defined by IR(t); and setting t.sub.opt to equal the day of the time coordinate of P.sub.3; and obtain a FIA by: computing a value v indicative of an integral of IR(t), between t.sub.L+1 and t.sub.opt, wherein t.sub.L+1 equals t.sub.L plus one day; and setting the FIA to equal v.
15. The system of claim 14, wherein the computing environment is further configured to generate, as output data, t.sub.opt and the FIA; wherein for ETa(t.sub.S)<IR(t.sub.S) the computing environment is further configured to: set t.sub.opt equal to t.sub.S; obtain a compensating forecast irrigation amount (cFIA) by: computing a value u.sub.1 indicative of an integral of IR(t) between t.sub.L+1 and t.sub.S; computing a value u.sub.2 indicative of an area S defined by the points P.sub.1 and P.sub.2 and a fourth point P4=(t.sub.S, IR(t.sub.S)); and setting the cFIA to equal u.sub.1+u.sub.2; and generate, as output data, t.sub.opt and the cFIA; and/or wherein the computing environment is further configured to set a next irrigation time t.sub.N equal to t.sub.opt.
16. The system of claim 14, wherein a next irrigation time t.sub.N is predetermined and wherein for ETa(t.sub.S)≥IR(t.sub.S) the computing environment is further configured to: if t.sub.N=t.sub.opt, generate, as output data, the forecast irrigation amount (FIA); and if t.sub.N≠t.sub.opt, obtain an adjusted FIA (aFIA) by: computing a second value v.sub.2 indicative of an area A defined by the points P.sub.1, P.sub.3, and a point P.sub.5=(t.sub.N, IR(t.sub.N)); if t.sub.N<t.sub.opt: setting the aFIA to equal FIA+v.sub.2; and if t.sub.N>t.sub.opt: setting the aFIA to equal FIA−v.sub.2; and generate, as output data, the aFIA; wherein for ETa(t.sub.S)<IR(t.sub.S), the system is further configured to: extrapolate the line L; obtain the point P.sub.5 and a point P.sub.6 defined by coordinates (t.sub.N, L(t.sub.N)); and obtain a compensating forecast irrigation amount (cFIA) by: computing a value w.sub.1 indicative of an integral of IR(t) between t.sub.L+1 and t.sub.N; computing a value w.sub.2 indicative of an area R defined by the points P.sub.1, P.sub.5, and P.sub.6; and setting the cFIA to equal w.sub.1+w.sub.2; and generate, as output data, the cFIA.
17. The system of claim 14, wherein for ETa(t.sub.S)<IR(t.sub.S) the computing environment is further configured to output an alert; wherein the computing environment is further configured to obtain Ks.sup.cur(t.sub.S) by computing a value indicative of a ratio of a first difference to a second difference; wherein the first difference is defined as a difference between a non-stress water potential taken at t.sub.S from a non-stress reference index of the crop, and the current crop water potential at t.sub.S; and wherein the second difference is defined as a difference between the non-stress water potential, and a maximum stress water potential taken at t.sub.S from a maximum stress reference index of said crop.
18. The system of claim 14, wherein the field comprises a plurality of subplots, said computing environment being configured to generate a set of irrigation plans, each plan comprising a subplot specific optimal irrigation time and a corresponding forecast irrigation amount; wherein the computing environment is further configured to have Ks.sup.cur(t.sub.S), ETa(t.sub.S), t.sub.opt, and the FIA permanently stored in the at least one computer-readable non-transitory storage medium, in a section thereof dedicated to the field; and/or wherein the computing environment is communicatively associated with at least one remote sensing apparatus and/or at least one in situ sensor, the current water potential being obtained using remote sensing data from the at least one remote sensing apparatus and/or in-situ measurement data from the at least one in situ sensor.
19. The system of claim 18, wherein the remote sensing data comprise images from one or more satellites, one or more drones, and/or one or more airplanes; wherein each pixel or a plurality of pixels in each of the images contains data corresponding to a respective area within the field or the subplot; wherein the remote sensing data are spectral reflectance data, thermal data, and/or radar data of the crop canopy; and/or wherein remote sensing data are thermal data or microwave data of the field soil.
20. The system of claim 19, wherein the computing environment is further configured to obtain one or more remote sensing derived indices using the spectral reflectance data, thermal data, and/or radar data of the crop canopy; and optionally, wherein the one or more remote sensing derived indices comprise at least one of the normalized difference water index (NDWI), derived from spectral reflectance data in the near infrared (NIR) and short wave infrared (SWIR) spectral bands, and the crop water stress index (CWSI), derived from crop and air temperature measurement data; or wherein the remote sensing data are spectral reflectance data in the red and infrared spectral bands, and optionally in the blue spectral band, allowing to obtain at least one of the normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI) therefrom.
21. The system of claim 14, wherein the computing environment is further configured to adjust the Kc values based on remote sensing data obtained during the growing period; and/or wherein the line L is straight.
22. The system of claim 14, wherein the computing environment is further configured to, subsequently to obtaining t.sub.opt: compute a current water stress coefficient Ks.sup.cur(t′.sub.S), wherein t.sub.S<t′.sub.S<t.sub.opt; compute an actual evapotranspiration (ETa) at t′.sub.S (ETa(t′.sub.S); and if ETa(t′.sub.S)≥IR(t′.sub.S): adjust t.sub.opt by: extrapolating a line L′ passing through or near first point P.sub.1, second point P.sub.2, and point P′.sub.2 defined by second coordinates (t′.sub.S, ETa(t′.sub.S)); obtaining a point P′.sub.3, whereat line L′ intersects, or is tangent to, the curve defined by IR(t); and setting t.sub.opt to equal the day of the time coordinate of P; and adjust the FIA by: compute a value v′ indicative of an integral of IR(t), between t.sub.L+1 and t.sub.N; and set the FIA to equal v′.
23. The system of claim 14, further comprising an irrigation controller, located near or within the field, the irrigation controller being configured to receive the output data generated by the computing environment, wherein the irrigation controller is configured to regulate irrigation by an irrigation infrastructure in the field according to the output data received from the computing environment; and/or wherein the line L is selected from a family of lines including curved lines.
Description
BRIEF DESCRIPTION OF THE FIGURES
(1)
(2)
(3)
(4)
(5)
(6)
(7)
(8)
(9)
(10)
(11)
(12)
(13)
DETAILED DESCRIPTION OF THE INVENTION
(14) The present invention provides methods and systems for forecasting and calculating precise irrigation needs of a crop in a specified area, and optionally delivering an irrigation plan to an end user and/or irrigation controller of an irrigation infrastructure. According to certain embodiments, the present invention performs a water requirement algorithm within a computing environment. The algorithm provides forecasting ahead for the required amount of water delivery based upon a combination of statistical values of historical crop-specific data and data obtained for the crop during the growing season.
(15) As used herein, the term “about” means approximately, in the region of, roughly, or around. A parameter or quantity is said to be “about”, or equal to “about”, a numerical value (e.g. an area equals about 1000 m.sup.2) when it is within a range, thereby extending the boundaries above and below the numerical values set forth. In general, the term “about” is used herein to modify a numerical value above and below the stated value by a variance of 10%. According to some embodiments, “about” is used herein to modify a numerical value above and below the stated value by a variance of 15%. According to some embodiments, “about” is used herein to modify a numerical value above and below the stated value by a variance of 20%.
(16) As used herein, the term “recent” with respect to data, such as measurement data from which the value of a physical quantity/parameter (e.g. crop water potential) is obtained (e.g. derived), refers to past measurement data within the growing period or season up until a day prior to the present time-point, for example, data of measurements carried out two days prior, one week prior, or even two weeks prior to the present time-point.
(17) As used herein, “current” with respect to a value of a physical quantity/parameter, such as crop water potential or actual evapotranspiration, refers to the present value or an estimated value of the physical quantity/parameter. The value can be determined based on measurement data obtained within the same (present) day and/or recent measurement data. In particular, measurement data obtained at given time-point(s) can be used to estimate (forecast) the value of a physical quantity at a later time-point (within the same growing period or season, e.g. several days after the first time-point(s)). When the later time-point coincides with the present time, the estimated value may be referred to as the current value.
(18) It is to be understood that reference to a current value as having been determined based on recent measurement data, covers the possibility that the current value is an estimated value derived from recent measurement data. For example, the current value of crop water potential may refer to an estimated value based on recent satellite imagery of the crop canopy and weather forecasts from around the time the satellite imagery was obtained. Further, for example, the current value of actual evapotranspiration may refer to an estimated value based on recent weather station data.
(19) As used herein, “reference data” refers to historical data from previous growing seasons or periods (e.g. growing seasons before the present growing season). The expressions “reference data”, “historical data”, and “archive” may be used interchangeably.
(20) The terms “growing period” and “growing season” are used herein interchangeably, and refer to the time of a crop growth cycle. The growing period is crop specific, and accordingly its start and/or end points may vary for each crop. According to certain embodiments, the growing period start point is at seeding or planting. According to other embodiments, when the crop is a perennial crop, particularly tree, the growing period start point is at bud break or after harvesting the yield of a previous growing period. According to certain embodiments, the growing period end point is at harvest and/or senescence of the crop plants.
(21) As described hereinbelow, “time” refers to a calendar day, to a time and date, to a day number as counted from the start of the growing season, to the time as measured from the start of the growing season, or to growing degree day (GDD).
(22) The systems and methods of the present invention are applicable to agricultural crops at a spatial resolution of irrigation blocks (subplots). The area of the irrigation blocks would depend on the resolution of the obtained in situ and/or spectral data, the obtained meteorological data, area of the entire field and the user (crop grower) needs. According to some embodiments, the subplot area is about 25 m.sup.2, about 1,000 m.sup.2, about 10,000 m.sup.2 (1 ha) or about 20,000 m.sup.2 (2 ha).
(23) According to certain embodiments, the system and methods of the present invention include several components, defining parameters and/or activities required to generate the irrigation plan.
(24) Data and Coefficients
(25) Weather Conditions
(26) The weather conditions are typically obtained from an online weather service record (online weather database) or from a meteorological station located in the vicinity of the field area to be irrigated, for example, within a distance of up to about 10 kilometers from the field. According to certain embodiments, the weather condition are obtained from a hyperlocal weather services which can specify the weather conditions to a resolution of several kilometers, for example 5 km×5 km. According to certain embodiments, the weather conditions are reflected by a value of daily evapotranspiration and/or mean daily evapotranspiration calculated for a known period (ET0). The function ET0(t), wherein t denotes time, represents the dependence of the evapotranspiration on the time t. According to some embodiments, the function ET0(t) is discrete, for example, when the time t specifies a day, a couple of days, or even a week or two weeks (i.e. the temporal resolution may be at the level of a day or a number of days). According to some embodiments, ET0(t) may be specified to within an hour or even minutes. According to some embodiments, ET0(t) is a continuous function, e.g. obtained by interpolating between a set of values of the evapotranspiration at different times. According to some embodiments, ET0(t) consists of three points, two points, or even a single point (i.e. ET0(t) is specified at three different times, two different times, or at a single time, respectively).
(27) As used herein, according to some embodiments, “time” refers to a calendar day, to a time and date, to a day number as counted from the start of the growing season, or to the time as measured from the start of the growing season. According to some embodiments, “time” refers to (i.e. is measured by) a growing degree day (GDD), in which case the “time” is possibly not linear in calendar days.
(28) Similarly, throughout the application, functions representing the time-dependence of physical quantities/parameters, scheduled operations, and the like, may be discrete or continuous, as explained above with respect to ET0(t). In particular, some time-dependent functions may be known in advance (pre-determined), e.g. when representing seasonal averages known in the art, or, for example, may be updated during the growing season as new data is accumulated (e.g. from weather stations, satellites, sensors in the field, etc.). In particular, when the function is discrete each update may involve increasing by one the number of points that define the function. For example, at the first day of the growing season evapotranspiration data may be received so that the function ET0(t) includes a single point: the value of ET0 at the time t.sub.1 (i.e. the first day). At the second day of the growing season new evapotranspiration data may be received so that the updated function ET0(t) includes two pointS; the value of ET0 at the time t.sub.1 and the value of ET0 at the time t.sub.2 (i.e. the second day), and so on. According to some embodiments, the received data includes an estimate (forecast) of the evapotranspiration at a later time-point (e.g. the next day, next week or even next two weeks). According to some embodiments, the received data together with weather forecast data are used to estimate the evapotranspiration at a later time-point. When the later time-point coincides with the present time, the received data may be referred to as recent data, and the current evapotranspiration may be referred to as having been derived (estimated) based on the recent measurement data. According to some embodiments, the received weather conditions can be used to estimate the evapotranspiration at an earlier time-point for which no data were available.
(29) According to certain embodiments, the value of ET0 at time t can be obtained from historical data representing seasonal averages of ET0.
(30) Last Irrigation Time (t.sub.L).
(31) The last irrigation time t.sub.L refers to the time (for example, in terms of a day) within the crop growing period in which irrigation has last been applied to the field or part thereof (irrigation block) to which the irrigation plan (the next irrigation amount and optionally the irrigation time) is to be provided.
(32) According to certain embodiments, at t.sub.L the crop received an amount of water to bring the crop water potential substantially to non-stress level.
(33) It is to be explicitly understood that the expression “last irrigation” encompasses any form of irrigation bringing the crop water potential to a non-stress or near non-stress level, including natural precipitations and agricultural irrigation.
(34) Crop Plant Water Potential
(35) The values of crop water potential can be obtained based on any method known in the art, including, but not limited to, in situ measurements of leaf and/or stem water potential of representative plants using plant sensors (e.g. pressure chambers); in situ measurements of soil water status, typically using soil moisture sensors; temperature and/or microwave data of soil moisture obtained by remote sensing (e.g. satellites); spectral and/or temperature data of crop canopy obtained by remote sensing (e.g. satellite or manned or unmanned airplane imagery) as described hereinbelow; images of crop canopy from towers located near or within the field, or from low-flying drones; and any combination thereof.
(36) Crop Coefficient (Kc)
(37) The Kc coefficient serves as a quantifier of the physical and physiological differences between crops. The crop coefficient Kc to be used with the teachings of the present invention can be obtained from published tabular values, for example those listed in FAO 56. According to the FAO recommendations, changes in vegetation and ground cover mean that the crop coefficient Kc varies during the growing period. Accordingly, the trends in Kc during the growing period are represented in a crop coefficient curve. Using the tabular values (reference Kc values), only three values for Kc are typically required to describe and construct the crop coefficient curve: those during the initial stage (Kc.sub.ini), the mid-season stage (Kc.sub.mid) and at the end of the late season stage (Kc.sub.end). Alternatively and/or additionally, crop canopy cover or reflectance data relying on remote sensing data can be used to obtain Kc throughout the growing period of the crop. The function Kc(t) represents the dependence of Kc on the time t.
(38) Kc relates the evapotranspiration ET0 to the non-stress evapotranspiration ETc. For given values of ET0 and Kc, the corresponding value of ETc is given by the product thereof, i.e. the non-stress evapotranspiration ETc.
(39) The function ETc(t), represents the dependence of ETc on the time t. In particular, ETc(t)=ET0(t)*Kc(t), wherein ET0(t) is the value of the evapotranspiration at a time t during the growing period.
(40) It is to be explicitly understood that Kc(t) values can be obtained from published values (i.e. reference or historical values) or can be derived from recent and/or present measurements. According to certain embodiments, Kc(t) values are derived from current data obtained using remote sensing.
(41) Today's commercially-available Earth observing satellite systems cover areas of thousands of square kilometers with pixels that define the image resolution from decimeters to tens of meters. Calculations at the regional scale are accomplished using data rasters in which values vary spatially across regions. The pixel size is an important consideration because it determines the resolution at which a field can be evaluated.
(42) According to certain embodiments, the remote sensing data are satellite imagery data. Typically, satellite imagery data may be given at a resolution of about 1,000 m.sup.2 (e.g. each pixel represents an area of about of 32 m×32 m). According to some embodiments, the satellite imagery data is of high resolution, with each pixel representing an area as small as about 25 m.sup.2.
(43) According to some embodiments, the remote sensing data include crop canopy reflectance data. According to certain embodiments the canopy reflectance is selected from the blue (B) band, green (G) band, red (R) band, near-infra-red (NIR) band, the short-wave-infrared-1 (SWIR1) band, the short-wave-infrared-2 (SWIR2) band and any combination thereof.
(44) According to some embodiments, one or more of the remote sensing derived indices are computed and the crop water potential and/or the crop coefficient Kc are obtained therefrom.
(45) According to certain embodiments, the remote sensing derived indices include, but are not limited to: (i) the normalized difference vegetation index (NDVI) defined via NDVI=(NIR−R)/(NIR+R); (ii) the enhanced vegetation index (EVI) defined via EVI=2.5*((NIR−R)/(NIR+6*R−7.5*B+1); (iii) the wide dynamic range vegetation index (WDRVI) defined via WDRVI=(0.2*NIR−R)/(0.2*NIR+R); (iv) the modified NDVI defined via (NIR−R)/(NIR+R−SWIR2); (v) the red-green simple ratio (R/G) defined via R/G; (vi) the blue-red simple ratio (B/R) defined via B/R; (vi) the Wetness index defines via (B*0.14+G*0.18+R*0.33+NIR*0.34−SWIR1*0.62−SWIR2*0.42) (viii) the normalized difference water index (NDWI) defined via (NIR−SWIR)/(NIR+SWIR); (ix) the SWIR−NIR index defined via (SWIR1+SWIR2)/(NIR); and (x) the crop water stress index (CWSI) defined via=(dT−dTl)/(dTu−dTl).
(46) In the description above, R and NIR stand for spectral reflectance measurements acquired in the red (visible) and near-infrared regions, respectively;
(47) G and B stand for spectral reflectance measurements acquired in the green and blue regions, respectively;
(48) SWIR stands for spectral reflectance measurements acquired in the short wave infrared region.
(49) Spectral reflectance is dimensionless being a ratio of the reflected radiation over the incoming radiation in the corresponding spectral band. Hence, the spectral reflectance assumes values between 0.0 and 1.0. By design, the NDVI thus varies between −1.0 and +1.0.
(50) dT is the difference between crop canopy temperature and air temperature; dTu is the upper limit of canopy temperature minus air temperature (non-transpiring crop); and dTl is the lower limit of canopy temperature minus air temperature (well-watered crop).
(51) According to some embodiments, the remote sensing data include thermal infrared images of the crop canopy, and the crop water potential, and/or the crop coefficient Kc are obtained therefrom.
(52) The inventors of the present invention have previously attempted mapping the crop coefficient (Kc) for cotton and process tomato based on Landsat-8 and Sentinel-2 satellite imagery on a field level. Data (not shown) were collected from 12 cotton plots and 5 tomato plots during the 2016 growing seasons. The dataset for each plot included vegetation height and crop cover, growth stage, irrigation timing and amounts, and the corresponding satellite imagery. For each crop, two of the plots were utilized to define the best imagery vegetation index to map the crop height and crop cover. These vegetation indices were then transformed into the cotton height and the tomato cover on a pixel and plot level for the rest of the plots. All the indices tested had an error of 15% or below, with a higher accuracy for the enhance vegetation index (EVI) and the normalized difference vegetation index (NDVI). These two indices were then utilized in published equations for calculating crop coefficient (Kc) and the values obtained were compared to the United Nations Food and Agriculture Organization Kc (Allen et al. 2009 ibid; FAO Irrigation and Drainage Paper No. 56). It was shown that the method used is suitable for mapping Kc on a field area level as small as 1 hectare (ha) (Beeri et al, 2017, The 11th European Conference on Precision Agriculture (ECPA 2017), Edinburgh, UK).
(53) Vegetation Moisture Stress Reference Indices (VMSRIs)
(54) Plant tolerance to water stress varies during the growing period of a crop plant. As used herein, plant tolerance refers to the plant capacity to recover after being exposed to a stress. The plant is recovered when at least one of growth, biomass, yield, fertilizer use efficiency, water use efficiency or a combination thereof is essentially not negatively affected by the stress. According to certain exemplary embodiments, the stress is a water stress.
(55) The present invention provides and utilizes three vegetation moisture stress reference indices:
(56) Non-Stress Reference Index
(57) The non-stress reference index describes the water potential of a crop plant or an average water potential value of a plurality of crop plants, as a function of time during the growing period thereof, when grown under non-limiting soil water conditions.
(58) Maximum-Stress Reference Index
(59) The maximum-stress reference index describes the most negative (i.e. the maximum in absolute value) water potential of a crop plant, or an average water potential value of a plurality of crop plants, as a function of time during the growing period thereof, when grown under limiting soil water conditions to which the plant is tolerant.
(60) Recommended Stress Reference Index (Also Referred to Herein as Irrigation Strategy)
(61) As described hereinabove, accumulated research has shown that deficit irrigation (i.e. irrigation at an amount less than the amount resulting in non-limiting soil water conditions) can provide high water efficiency and/or crop productivity in terms of costs and yield. In addition, crops often have varying water stress sensitivity at different growth stages, and thus the plant may be subjected to more stress at periods when the stress will have a smaller impact on yield. The recommended stress reference index reflects the time-dependence of the recommended water potential of a crop plant during the crop growing period. The recommended stress index is presented in
(62) Typically, the VMSRIs are obtained using historical data (seasonal averages). According to some embodiments, the VMRSIs can be adjusted during the growing season.
(63) Methods
(64) Ks Computation
(65) The present invention now provides a novel computational method to set a Ks value. In certain embodiments, the computed Ks value is based, inter alia, on present and/or recent measurements, thus reflecting the actual stress the crop is experiencing (Ks.sup.cur). According to certain embodiments, the computed Ks value is derived using a recommended stress reference index of the crop to be irrigated (Ks.sup.ex).
(66) Making reference to
(67) Also indicated in
(68) The method for calculating Ks.sup.cur/Ks.sup.ex includes: Obtaining a current water potential of a crop at t′ (the value of the current water potential is given by the y (vertical) coordinate of G) from current and/or recent measurement data; or obtaining a recommended water potential of the crop at t′ (given by the y coordinate of B.sub.1) from the recommended stress reference index of the crop. Computing a first difference between the non-stress water potential value at t′ (given by the y coordinate of B.sub.2), which is obtained from the non-stress reference index of the crop, and the current water potential of the crop at t′, or the recommended water potential of the crop at t′. Computing a second difference between the non-stress water potential value and the maximum stress water potential value at t′ (given by the y coordinate of B.sub.3), which is obtained from the maximum stress reference index. Computing a ratio, or a value indicative thereof, of the first difference to the second difference (i.e. E.sub.1/D.sub.2 or D.sub.1/D.sub.2), wherein the computed ratio value is Ks.sup.cur or Ks.sup.ex, respectively.
(69) E.sub.1, which designates the distance between G and B.sub.2, indicates the first difference when computed using the current water potential of the crop (i.e. as obtained from present and/or recent measurements). D.sub.1, which designates the distance between B.sub.1 and B.sub.2, indicates the first difference when computed using the recommended stress reference index of the crop. D.sub.2, which designates the distance between B.sub.3 and B.sub.2, indicates the second difference.
(70) When the computation of Ks is based on present and/or recent water potential measurements, Ks is referred to herein as current Ks (Ks.sup.cur). The function Ks.sup.cur(t) gives the dependence of Ks.sup.cur on time (e.g. on the calendar day).
(71) When the computation of Ks is based on the recommended stress reference index, Ks is referred to herein as expected Ks (Ks.sup.ex). The function Ks.sup.ex(t) gives the dependence of the Ks.sup.ex on time.
(72) Actual Crop Evapotranspiration ETa
(73) The actual evapotranspiration of a crop is obtained by taking the product of the non-stress evapotranspiration of the crop ETc and Ks.sup.cur. When Ks.sup.cur=1, the actual evapotranspiration of the crop equals the non-stress evapotranspiration of the crop.
(74) The function ETa(t), represents the dependence of ETa on the time t. The actual crop evapotranspiration at time t (ETa(t)) is computed by the equation:
ETa(t)=ET0(t)*Kc(t)*Ks.sup.cur(t)=ETc(t)*Ks.sup.cur(t)
(75) It is to be explicitly understood that the values of ET0 and Ks.sup.cur are not necessarily obtained from respective measurement data corresponding to the same time. For example, ETa(t.sub.a) can be obtained from Ks.sup.cur measurement data corresponding to a measurement performed at t.sub.a, and ET0 measurement data corresponding to a measurement performed at a time t.sub.b>t.sub.a. The value of ET0 at time t.sub.a is then deduced from the value thereof at t.sub.b. Such a scenario is pertinent, for example, when at time t.sub.a no measurement data was available to derive ET0(t.sub.a).
(76) According to some embodiments, both Ks.sup.cur and ET0 are obtained from recent or present measurement data. Kc(t) can be obtained as described hereinabove.
(77) Irrigation Recommendation (IR)
(78) An irrigation recommendation function IR(t) gives the recommended daily amount of water to be applied to a crop during the growth period. An irrigation recommendation for an entire growth period can be computed according to the FAO No. 56 instructions (ibid) and further publications (for example Allen R G and Pereira L S., 2009. Irrig Sci 28:17-34). Irrigation recommendation may be also based on data obtained for specific crops (for example, Conceição N et al., 2017. Agricultural Water Management 191:138-152; Kopyt M and Tsadok S., Grapegrower & Winemaker July 2015, pp. 44-48).
(79) According to certain embodiments, the IR function utilized with the teachings of the present invention is essentially based on daily values of ET0, Kc and Ks.sup.ex. More specifically, IR(t)=ET0(t)*Kc(t)*Ks.sup.ex(t). According to some embodiments, ET0 values used in obtaining the function IR(t) are historical corresponding to seasonal averages of ET0. According to some embodiments, ET0 values used in obtaining the function IR(t) are values obtained during the growing season (i.e. recent and present and forecast for the next week or two). In such a scenario the function IR(t) is progressively obtained with the progress of the growing season, as new ET0 values are obtained/derived/forecasted.
(80)
(81) Computation of the Forecast Irrigation Amount (FIA) at a Next Irrigation Time t.sub.N Relative to the Last Irrigation Time t.sub.L
(82) The present invention now discloses novel computational methods to determine the amount of irrigation that should be applied to a crop to maintain the water potential at and/or between the recommended stress and the non-stress water potential of the crop, as well as determining the optimal time for applying the irrigation. It is to be understood that the term “optimal” used herein with respect to irrigation time refers to the most recommended time point (present or future) for irrigation based on the methods of the present invention.
(83)
(84) Steps 310-340, steps 350-375, and steps 380-395 are outlined in
(85) A next irrigation time t.sub.N is defined by the day on which t.sub.opt falls, i.e. t.sub.N is set equal to t.sub.opt. According to some embodiments,
(86)
According to some embodiments, for example, embodiments wherein IR(t) is a discrete function, specified by daily values,
(87)
(88) Steps 350-370 in a specific embodiment of method 300 are depicted in
(89) In
(90) Line L, which in
(91) It is noted that not all of the data received at step 310 need necessarily be received at the same time, e.g. at t.sub.S (even when t.sub.S is specified to within a day, i.e. represents a day). For example, the evapotranspiration may be estimated on a weekly basis, or even every two weeks, in which case the evapotranspiration may be obtained prior to t.sub.S, e.g. two days or three days before, while at t.sub.S data indicative of the plant water potential are received.
(92) The data received at step 310 may be received from weather stations (i.e. evapotranspiration data), satellites (remote sensing data), from an online server receiving data from various sources, for example data from multiple satellites and weather services, and the like, as elaborated on below.
(93)
(94) It is noted that τ.sub.L=t.sub.N and Q.sub.1=(τ.sub.L, ETc(τ.sub.L)). In a repetition of step 310, values of a current crop water potential at τ.sub.S and an evapotranspiration at τ.sub.S (ET0(τ.sub.S)) are obtained. Steps 320-370 are then repeated to obtain τ.sub.opt (and τ.sub.N, which equals τ.sub.opt) and a corresponding FIA. Specifically, Q.sub.2=(τ.sub.S, ETa(τ.sub.S)), wherein ETa(τ.sub.S) is the actual evapotranspiration at τ.sub.S obtained in the repetition of step 330. In the repetition of step 350 a line λ is extrapolated passing through or near Q.sub.1 and Q.sub.2. A point Q.sub.3 indicates the point whereat λ (first) intersects or is (first) tangent to IR(t). τ.sub.opt(=τ.sub.N) equals the day of the time coordinate of Q.sub.3.
(95) While
(96) According to some embodiments of method 300, when ETa(t.sub.S)≥IR(t.sub.S), following step 360, wherein t.sub.opt is determined, additional measurement data may be obtained corresponding to a time t′.sub.S later than t.sub.S, but before t.sub.opt (i.e. t.sub.S<t.sub.S<t.sub.opt). The optimal irrigation time (and consequently the next irrigation time) and the FIA may then be accordingly adjusted. For example, additional measurement data corresponding to a time t′.sub.S are obtained, from which an actual evapotranspiration at t′.sub.S (ETa(t′.sub.S)) is obtained (by repeating steps 310-330 with respect to the additional measurement data). Line L may then be extrapolated (or adjusted) taking into account an additional point P′.sub.2=(t′.sub.S, ETa(t′.sub.Ss)), as depicted in
(97) Steps 380-390 in a specific embodiment of method 300 are depicted in
(98)
(99) Steps 505-520, steps 525-558, and steps 560-575 are outlined in
(100) Steps 525 to 545, when t.sub.opt<t.sub.N, in a specific embodiment of method 500 are depicted in
(101) Steps 560 to 570 in a specific embodiment of method 500 are depicted in
(102) While in
(103) It is noted that while in
(104) It is to be understood that when a field contains a number of subplots, methods 300 and 500 may be executed with respect to each of the subplots. Subplot specific irrigation plans may be desirable when the field area is such that the subplots may vary from one another in, for example, geographical parameters. For example, in a mountainous region, subplots may differ in the amount exposure to sunlight or, in flat topography, subplots may differ because of soil. In addition, subplots may vary in the density of crops. Subplot specific irrigation plans can also address the case wherein different crops are planted at different subplots, respectively.
(105) According to another aspect, the present invention provides a system for managing agricultural irrigation of a crop in a field or a part thereof. Generally, the system is configured to manage agricultural irrigation of a plurality of crops in a plurality of fields.
(106) Computing environment 702 includes at least one memory 712 (a computer-readable storage medium generally including non-volatile and volatile memory components), one or more computer processors 714 operably coupled to memory 712, and a communication unit 716 configured to send/receive data to/from external targets/sources. Memory 712 may be any suitable data storage device, including volatile memory types such as random access memory, DRAM, SDRAM, and others. Memory 712 may also include non-volatile memory, including read only memory, EEPROM, flash memory, optical and magnetic computer memory storage devices, and others. Memory 712 stores computer-executable instructions for executing one or more of the methods of the present invention, such as method 300 and 500. Computer processors 714 are configured to execute the computer-executable instructions, as further elaborated on below in the description of
(107) Generally, computing environment 702 will be at least one online server (wherein at least one online server constitutes a “cloud environment”) providing services (e.g. irrigation plans) to clients—e.g. smart phones (of users of system 700) with custom software (application), as elaborated on below. The software may be: qualified by one or more smart phone manufacturers; launched automatically once the hardware device, such as an irrigation controller (752, described hereinbelow) is paired with the smart phone; and/or the main console for the user (e.g. a personal computer 724, described hereinbelow). The software application may provide all necessary instructions. The software application may allow a user of system 700 to initiate a data collection sequence by use of a predefined action, e.g. to collect measurement data from in situ sensors (736, described hereinbelow). The software application may gather data entered by the user of system 700, such as whether recommendation supplied by system 700 were or are being implemented, forward such data as user input data (812, described in
(108) Input data may be obtained from a user of system 700, via e.g. a user-controlled input data source, such as a smart phone 722, a tablet (not shown), and/or a personal computer 724 of the user, which may have a custom application (app) installed thereon, as further elaborated on below. Additional input data sources include climatology data sources, such as one or more weather services and networks (not shown), one or more local weather stations 732, as further elaborated on below.
(109) The input data sources further include remote sensing data sources, and/or in-situ sensor data sources obtained from one or more sensors 736. According to some embodiments, sensors 736 are communicatively associated with computing environment 702, for example, via Wi-Fi transmitters included in sensors 736. Remote sensing data may be spectral (measuring crop canopy reflectance), thermal (measuring the crop canopy and/or soil temperature), radar (measuring the crop echo), microwave (measuring the soil moisture) and/or data obtained from other systems similar to radar which make use of other parts of the electromagnetic spectrum (such as LiDAR), and may be obtained from one or more satellites 742, one or more drones 744, and one or more (manned or unmanned) airplanes (not shown). Satellites 742 can be, for example, fine temporal resolution low-earth orbit satellites that provide a minimum of three spectral bands and other resource-monitoring satellites, and/or lower temporal frequency earth resources satellites. Examples of in-situ sensors 736 include pressure chambers and soil moisture sensors.
(110) Output data targets include users of system 700, or more precisely, remote devices of the users, such as smart phones, tablets, and/or personal computers, for example, smart phone 722 and personal computer 724. Specifically, computing environment 702 is configured to send irrigation plan to users of system 700, as further elaborated on below. Other possible output data targets include irrigation infrastructures, such as an irrigation infrastructure 750 located in field 704. Irrigation infrastructure 750 includes irrigation elements such as a drip irrigation system, sprinklers, and the like, and an irrigation controller 752 configured to regulate (control) irrigation (e.g. start, stop, increase rate) by the irrigation elements. More specifically, irrigation controller 752 is configured to regulate the irrigation of field 704 according to irrigation instructions received from computing environment 702. According to some embodiments, system 700 includes at least one irrigation controller such as irrigation controller 752.
(111)
(112) User input data 812 will generally include field area boundaries (e.g. field 704 boundaries), crop type and variety, season start (start of the crop growing period), season end (end of the growing season), irrigation method (e.g. drip irrigation or sprinklers) and optionally start and end of the last irrigation/precipitation, and additional field parameters (e.g. soil texture, soil and water salinity, organic matter, irrigation rate).
(113) Climatology data 814 include ET0 and/or T.sub.max, T.sub.min, <T> (T average), radiation, relative humidity, precipitation, and wind speed per field managed by system 700. Climatology data 814 may be obtained, for example, from one or more weather services and/or one or more local weather stations (e.g. within 5-10 km of the managed field, such as local weather stations 732, which are located nearby field 704).
(114) Remote sensing data 816 include spectral and/or thermal and/or radar and/or microwave crop and/or soil data from which the water potential of a crop in a field may be obtained. According to some embodiments, remote sensing data 816 are raw (“Level 0”) in the form of camera outputs of a drone or an airplane (in particular, without any location information). According to some embodiments, remote sensing data 816 are “Level 1” (including location information), for example, Landsat images obtained from the National Aeronautics Space Administration (NASA). According to some embodiments, remote sensing data 816 are “Level-2” (including location information, and wherein pixel values are given in physical units (such as reflectance or temperature), for example, Sentinel-2 images from the European Space Agency (ESA).
(115) In-situ sensors data 818 includes measurement data from in-situ sensors in managed fields (such as in-situ sensors 736 in field 704), which, according to some embodiments, specifies, or can be used to derive, the water potentials of the crops within each field, respectively.
(116) Input data 802 is ingested by a data ingest module 822. The ingested data is stored (permanently or temporarily) in memory 712 (i.e. in databases 832) and transferred to one or more data processing modules 826. Databases 832 generally include an agricultural database storing data specifying, e.g. Kc tables and vegetation moisture stress reference indices of different crops, and a managed-fields database storing data associated with each of fields managed by system 700, optionally including historical data. The managed-fields database is partitioned into different sections dedicated to each field.
(117) Data processing modules 826 include an irrigation recommendation computing (IRC) module 836. IRC module 836 is configured to obtain an actual evapotranspiration, designated by 842, from input data 802 together with data stored in databases 832 (e.g. Kc tables, crop VMSRIs). For example, following an irrigation of field 704 at t.sub.L and receipt of input data 802 from which the water stress coefficient at t.sub.S (>t.sub.L), Ks.sup.cur(t.sub.S), is obtained/derived, IRC module 836 computes ETa(t.sub.S), as described above in the description of methods 300 and 500. IRC module 836 is further configured to obtain the optimal irrigation time t.sub.opt, designated by 844, and a recommended irrigation amount (e.g. the forecast irrigation amount (FIA), the adjusted FIA (aFIA), and the compensating FIA (cFIA)), designated by 846, using ETa 842 and data stored in databases 832, as described hereinabove in the description of
(118) Output data 850, e.g. an irrigation plan 852 and/or alert 854 (alerting a user that irrigation of a respective field is late, as determined in step 340 in method 300 and in step 520 in method 500), generated by data processing modules 826, are conveyed therefrom to an output module 860, and generally also to databases 832 for future use and reference. In particular, output data 850, as well as other data generated by IRC module 836 with respect to a field 704 stored in a corresponding section of databases 832. Output module 860 sends output data 850 to output data targets 862, such as one or more remote devices 866 (e.g. smart phone 722, personal computer 724), irrigation controller 752, and application programming interfaces (APIs) 868.
(119)
(120) Image-processing modules 918 are configured to analyze remote-sensing imagery data. According to some embodiments, image-processing modules 918 are used in converting Level-0 or Level-1 imagery data into Level-2 imagery data.
(121) GIS module 926 may be configured to match (and/or confine) the images to the field boundaries, remove cloud effects and atmospheric effects and to calculate an individual recommendation for each subplot. According to some embodiments, GIS module 926 removes pixels at the extreme ends of a scale (e.g. an intensity scale) or pixels having at least one component at an extreme end of a scale.
(122) RSDI computing module 934 is configured to receive data from image-processing modules 918, and optionally GIS module 926 and convert the received data into one or more water stress indices such as the normalized difference water index (NDWI) or the crop water stress index (CWSI), and vegetation indices such as NDVI and EVI or combination of the above with radar and/or thermal information.
(123) CWP computing module 942 is configured to receive data from RSDI computing module 934 and to convert the received data into the water potential of the crop. According to some embodiments, CWP module 942 is additionally configured to receive, and take into account in computing the water potential, data from in-situ sensors 736. According to some embodiments, not depicted in
(124) According to some embodiments that include Kc computing module 910, Kc computing module 910 is configured to obtain the value of the crop coefficient Kc based on vegetation index data obtained from RSDI computing module 934 or other irrigation protocols (such as the FAO-56), and optionally, climatology data 814, e.g. wind speed and relative humidity.
(125) Ks.sup.cur computing module 902 is configured to compute a current water stress coefficient Ks.sup.cur (e.g. at t.sub.S) based on the current crop water potential (which is received from CWP module 942), and vegetation moisture stress reference indices (VMSRIs) stored in databases 832 as schematically demonstrated in
(126) In situ measurements computing module 946 is configured to receive data from in situ-sensors 736 and to process the data from the different sensors, e.g. to geo-statistically average readings from the different sensors to obtain measurement values representative of the irrigation block. According to some embodiments, in-situ measurements computing module 946 outputs are assigned location information by GIS module 926. According to some embodiments, in-situ measurements computing module 946 outputs are used by CWP module 942 to compute water potentials of plants located in different irrigation blocks.
(127) ML/AI modules 950 are configured to improve computing environment 702 irrigation plans by analyzing, for example, past recommendations during a past growing season (or a part thereof) and measurement data of the crops during the past growing season, as well as optionally climatology data during the growing season and the crop yield at the end of the season, and/or the like. For example, according to some embodiments, ML/AI modules 950 are configured to adjust the fitting procedure deriving line L in step 350 of method 300 (or step 525 of method 500), thereby potentially modifying the obtained value of the optimal irrigation time in step 360 (or step 530) and the determined FIA in step 370 (or step 535). Similarly, according to some embodiments, ML/AI modules 950 are configured to adjust the shapes and sizes of area S in step 390 of method 300, and areas A and R in steps 545 and 570 of method 500, respectively. According to some embodiments, wherein Kc is obtained/computed using also remote sensing imagery data, ML/AI modules 950 are configured to improve the determination of Kc based on historical data (reference Kc tables) and (past) measurement data and also optionally measurement data of the field (and the crop) from preceding seasons.
(128) The methods of the present invention, such as methods 300 and 500, may be implemented by many different computing environments. For example, computing environment 702 may include a special purpose computer, a programmed microprocessor or microcontroller, and peripheral integrated circuit element(s), an ASIC or other integrated circuit, a digital signal processor, an image processor (e.g. to covert Level-0 or Level-1 imagery data to Level-2 imagery data), electronic or logic circuitry such as discrete element circuit, a programmable logic device or gate array such as a PLD, PLA, FPGA, PAL, and any comparable means.
(129) The term “microprocessor”, or “microcontroller” as used herein, refers broadly without limitation, to a computer system, a computer equivalent, or a processor which is designed to perform arithmetic and/or logic operations using logic circuitry that responds to and processes the basic instructions that drive a computer. Thus, the term “microprocessor” refers to any device comprising a programmable digital electronic component that incorporates the functions of a central processing unit (CPU) on a single semiconducting integrated circuit (IC). Typical computer systems may comprise one or more microprocessors. Therefore, the term “microprocessor” as used herein, typically refers to a device comprising at least one microprocessor.
(130) In general, any means of implementing the methods disclosed herein, such as methods 300 and 500, can be used to implement the various aspects of the present invention. Exemplary hardware that can be used for the present invention includes computers (e.g. a cloud-based computing environment, according to some embodiments of computing environment 702), handheld devices (e.g. a tablet of a user of system 700), telephones (e.g., cellular, Internet enabled, digital, analog, hybrids, and others), such as smart phone 722, and other such hardware. Some of these devices include processors (e.g., a single or multiple microprocessors), memory, nonvolatile storage, input devices, and output devices. Furthermore, alternative software implementations including, but not limited to, distributed processing, parallel processing, or virtual machine processing can also be configured to perform the methods described herein.
(131) The systems and methods of the present invention may also be partially implemented in software that can be stored on a storage medium, non-transitory or otherwise, executed on programmed general-purpose computer with the cooperation of a controller and memory, a special purpose computer, a microprocessor, or the like. In these instances, the systems and methods of this invention can be implemented as a program embedded on personal computer such as an applet, JAVA or CGI script, as a resource residing on a server or computer workstation, as a routine embedded in a dedicated measurement system, system component, or the like. The system can also be implemented by physically incorporating the system and/or method into a software and/or hardware system.
(132) Additionally, the data processing operations disclosed herein may be performed by one or more program instructions stored in or executed by such memory, and further may be performed by one or more modules (e.g. data processing modules 826) configured to carry out those program instructions. “Modules” refer to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, expert system or combination of hardware and software that is capable of receiving, sending, storing, and/or processing data according to the described functionality thereof.
(133) As used herein, according to some embodiments, “remote sensing apparatus” refers to a satellite, a drone, and/or an airplane having means configured for remote sensing.
(134) The foregoing description of the specific embodiments will so fully reveal the general nature of the invention that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without undue experimentation and without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. The means, materials, and steps for carrying out various disclosed functions may take a variety of alternative forms without departing from the invention.