A system for autonomous monitoring and/or optimization of plant (140) growth is provided. The system may include actuation devices configured to interact with an agricultural area (120), image sensors (130) configured to capture images (170) of a plant (140) in the agricultural area (120), and a processor (150) in communication with the image sensors (130) and the actuation devices. The processor (150) may be configured to store, via a memory (160), a first image (170) of the agricultural area (120) captured prior to a first actuation of the actuation devices; and trigger, synchronously with the first actuation, the image sensors (130) to capture a second image (180) of the agricultural area (120). The processor (150) may be further configured to detect features of the plant (140) in the first and second images (170) of the agricultural area (120); evaluate the detected features of the plant (140) for visual plant qualities (210); and dynamically set one or more parameters (190) of the actuation devices based on the visual plant qualities (210).

There is disclosed a method and system for regulating plant irrigation at a crop field. The method comprises obtaining soil water tension (SWT) data and/or soil water content (SWC) data corresponding to a crop field. The SWT data and/or the SWC data is segmented into three segments. A respective line of best fit is determined for each of the three segments. The intercepts of the lines of best fit are used to determine an irrigation start threshold and an irrigation stop threshold. Devices that control irrigation for the crop field are caused to start or stop irrigation based on the irrigation start threshold and irrigation stop threshold.

Systems, processes and methods for controlling the irrigation of wastewater to a vegetated land are provided. The process can include determining a drained upper limit (DUL)-related criterion of an irrigation zone of the vegetated land, and obtaining a soil water tension measurement indicative of the irrigation status in the irrigation zone. The soil water tension measurement can then be compared to the DUL-related criterion, and when the soil water tension measurement of the irrigation zone is equal to or above the DUL-related criterion, an irrigation event characterized by a given volume of wastewater and a given irrigation duration can be initiated to irrigate the irrigation zone. The process can also include implementing a predetermined irrigation protocol in accordance with a set of predetermined parameters to irrigate the irrigation zone during an irrigation event, the set of predetermined parameters including for instance a DUL-related criterion for the irrigation zone.

Disclosed are various embodiments for reinforcement learning-based irrigation control to maintain or increase a crop yield or reduce water use. A computing device may be configured to determine an optimal irrigation schedule for a crop planted in a field by applying reinforcement learning (RL), where, for a given state of a total soil moisture, the computing device performs an action, the action comprising waiting or irrigating crop. An immediate reward may be assigned to a state-action pair, the state-action pair comprising the given state of the total soil moisture and the action performed. The computing device may instruct an irrigation system to apply irrigation to at least one crop in accordance with the optimal irrigation schedule determined, where the optimal irrigation schedule includes an amount of water to be applied at a predetermined time.

Soil moisture monitoring systems and methods for measuring mutual inductance of area of influence using radio frequency stimulus are disclosed herein. An example device includes a master element stacked vertically on top of one or more slave elements. The master element and slave elements can communicate through a 1-wire bus configuration. The master element can determine the presence and location of each of the one or more slave elements using an auto-discovery process. The master element can issue commands to the one or more slave elements to obtain moisture readings and/or temperature readings.

A plant water need computing system and method for forecasting water need to optimize irrigation efficiency while ensuring that a plant grows at optimal water availability. The plant water need computing system and method use a computational input and output balance model (CIOB model) implemented on a server to calculate irrigation need (IR) predictively. The CIOB model is implemented as a service through a representational state transfer application program interface (REST API). Registered clients get access to the API through a client application. Field identifier is passed by the client application to the CIOB model in an API request. The CIOB model sends an API response to the client application. The API response comprises irrigation need (IR). The CIOB model uses a computational module to calculate the IR and uses machine learning to optimize the plant water need.

A computerized crop growing management system (CMS) for a farm includes a main controller with an associated user interface (UI). The farm has a plurality of fields on each of which a different crop may be raised, each crop having different irrigation and nutrient requirements. Each field is fed by a main irrigation line connected to a network of irrigation pipes having controller-based valves. Sensors monitor growing conditions in each field. The UI is configured to permit an operator to monitor growing conditions, and control the supply of irrigation liquid and nutrients to each field and/or each crop. The UI allows the operator to specify and create irrigation schedules, nutrient recipes and flow rates, as well as warn an operator of technical and crop problems.

There is provided a smart drip irrigation emitter to provide intelligent features including on-demand watering, sensors and communication links. The emitters can be activated by a wireless signal to power and/or control water delivery from the emitter. The emitter also may include sensors that gather data pertaining to an individual plant. Based on the data received by the sensors, the emitter intelligently determines whether to water the plant. The smart emitter can form a communication network with other smart emitters.

There is provided a smart drip irrigation emitter to provide intelligent features including on-demand watering, sensors and communication links. The emitters can be activated by a wireless signal to power and/or control water delivery from the emitter. The emitter also may include sensors that gather data pertaining to an individual plant. Based on the data received by the sensors, the emitter intelligently determines whether to water the plan. The smart emitter can form a communication network with other smart emitters.

In some embodiments, apparatuses and methods are provided herein useful to use with irrigation devices connected to a multi-wire path in an irrigation system. In some embodiments, there is provided a system for use with irrigation devices including a modulator configured to provide an output power signal modulated with data; a multi-wire interface coupled to the modulator and configured to electrically couple to the multi-wire path extending into a landscape and to which the irrigation devices are connected; and a control circuit configured to execute an automated device discovery process configured to cause the modulator to modulate data comprising a discovery message on the output power signal, the discovery message indicating a portion of an address to match and prompting a response from one or more of the irrigation devices in which a corresponding portion of the unique address matches the portion of the address to match.