Dynamic Determination of Irrigation-Related Data Using Machine Learning Techniques

A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to:

• obtain multiple items of irrigation-related data pertaining to at least one region of interest;
• determine one or more temporal values corresponding to irrigation activity at one or more portions of the at least one region of interest by performing spatiotemporal analysis of at least a portion of the obtained irrigation-related data;
• determine one or more amounts of water utilized in connection with the irrigation activity corresponding to the one or more determined temporal values by applying a first set of one or more machine learning techniques to at least a portion of the obtained irrigation-related data;
• determine one or more types of irrigation activity to be attributed to the irrigation activity corresponding to the one or more determined temporal values by applying a second set of one or more machine learning techniques to (i) at least a portion of the obtained irrigation-related data and (ii) the one or more determined amounts of water utilized in connection with the irrigation activity;
• determine one or more irrigation-related variables pertaining to the at least one region of interest by executing a physical model using, as inputs, (i) the one or more determined temporal values, (ii) the one or more determined amounts of water utilized in connection with the irrigation activity, and (iii) the one or more determined types of irrigation activity to be attributed to the irrigation activity, wherein the one or more irrigation-related variables comprises at least an extent of the irrigation activity;
• and
• output the one or more determined irrigation-related variables to at least one user.

A system comprising:

• a memory;
• and
• at least one processor operably coupled to the memory and configured for:
• obtaining multiple items of irrigation-related data pertaining to at least one region of interest;
• determining one or more temporal values corresponding to irrigation activity at one or more portions of the at least one region of interest by performing spatiotemporal analysis of at least a portion of the obtained irrigation-related data;
• determining one or more amounts of water utilized in connection with the irrigation activity corresponding to the one or more determined temporal values by applying a first set of one or more machine learning techniques to at least a portion of the obtained irrigation-related data;
• determining one or more types of irrigation activity to be attributed to the irrigation activity corresponding to the one or more determined temporal values by applying a second set of one or more machine learning techniques to (i) at least a portion of the obtained irrigation-related data and (ii) the one or more determined amounts of water utilized in connection with the irrigation activity;
• determining one or more irrigation-related variables pertaining to the at least one region of interest by executing a physical model using, as inputs, (i) the one or more determined temporal values, (ii) the one or more determined amounts of water utilized in connection with the irrigation activity, and (iii) the one or more determined types of irrigation activity to be attributed to the irrigation activity, wherein the one or more irrigation-related variables comprises at least an extent of the irrigation activity;
• and
• outputting the one or more determined irrigation-related variables to at least one user.

A computer-implemented method comprising:

• determining one or more temporal values corresponding to irrigation activity at one or more portions of at least one region of interest by performing spatiotemporal analysis of one or more backscattering parameters derived from microwave satellite data associated with irrigation-related data;
• determining one or more amounts of water utilized in connection with the irrigation activity corresponding to the one or more determined temporal values by applying a first set of one or more machine learning techniques to at least a portion of the irrigation-related data and the one or more backscattering parameters;
• determining one or more types of irrigation activity to be attributed to the irrigation activity corresponding to the one or more determined temporal values by applying a second set of one or more machine learning techniques to (i) at least a portion of the irrigation-related data and (ii) the one or more determined amounts of water utilized in connection with the irrigation activity;
• determining an extent of the irrigation activity by executing a physical model using, as inputs, (i) the one or more determined temporal values, (ii) the one or more determined amounts of water utilized in connection with the irrigation activity, and (iii) the one or more determined types of irrigation activity to be attributed to the irrigation activity;
• and
• performing one or more automated actions in response to (i) the one or more determined temporal values, (ii) the one or more determined amounts of water utilized in connection with the irrigation activity, (iii) the one or more determined types of irrigation activity to be attributed to the irrigation activity, and (iv) the determined extent of the irrigation activity;
• wherein the method is carried out by at least one computing device.