Adaptive learning drought region crop growth prediction system and method

The adaptive learning-based crop growth prediction system for arid regions utilizes the fusion of ground and remote sensing data to construct a multi-dimensional state-space model, solving the quantification problem of nonlinear response of crop growth in arid regions and achieving optimized resource allocation and improved prediction accuracy.

CN122288041APending Publication Date: 2026-06-26SHAANXI SCI TECH UNIV
4 Cites 0 Cited by

Patent Information

Application Number
CN202610629727.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-05-09
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing technologies cannot effectively quantify the nonlinear response of different water supply conditions to crop growth in arid areas, making it difficult to optimize resource allocation under limited water resources conditions. Furthermore, the models are prone to prediction drift and misjudgment in complex dynamic environments.

Method used

By constructing an adaptive learning-based crop growth prediction system for arid regions, a multi-dimensional state-space model is generated by fusion of ground point source environmental data and regional remote sensing physiological image data at spatiotemporal scales. This model is then combined with physiological response sensitivity parameters to perform difference equation simulations, and the marginal yield loss matrix is ​​adjusted in real time to achieve optimal resource scheduling.

Benefits of technology

It improves the accuracy and robustness of agricultural resource allocation decisions in arid areas, reduces prediction drift and misjudgment in complex environments, and achieves differentiated and precise resource allocation.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses an adaptive learning arid region crop growth prediction system and method, and relates to the field of growth prediction. The method comprises the following steps: synchronously acquiring ground environment data, remote sensing physiological images and historical yield, generating environment reference features and physiological representation vectors, and further constructing a multi-dimensional state space model; inputting the model into a dynamic model containing physiological response sensitivity parameters, and simulating and generating an expected growth trajectory set under various water supply conditions through a difference equation; constructing a marginal yield loss matrix on the basis, and outputting a difference resource allocation vector of each sub-region under the constraint of the total water resource; in addition, a crop growth model is dynamically corrected and a marginal yield loss matrix is adjusted by using a deviation residual between a real-time physiological feature value and a predicted trajectory. According to the invention, accurate simulation of the crop growth state and optimal scheduling of water resources are realized, and the system has adaptive learning and disaster-resistant and loss-reducing capabilities.
Need to check novelty before this filing date? Find Prior Art