SBIR Phase I: Developing a generative framework to assess farmland resilience based on artificial intelligence, satellite data, and stochastic weather modeling

这个小企业创新研究（SBIR）第一阶段项目的更广泛的影响是定量评估农田状况和恢复力。该项目研究受天气和静态土壤和景观特性影响的不同农业生产力。这项研究将开发使用人工智能进行预测的模型。 它将基于来自美国和世界其他农业密集地区的数据，允许将该框架推广到新的地理领域。模型还将在玉米、大豆、小麦和水稻等多种主要作物上进行测试，该系统将包括一个供未经培训的用户使用的界面，以及用于定量金融分析的重要数据。SBIR第一阶段项目旨在开发一个集成的机器学习框架，包括最先进的生成天气模型，特征转换模型和作物产量模型，以获得丰富的模拟生长季节环境条件和相关产量估计。在过去20年的高分辨率卫星图像的支持下，该模型不仅能够捕捉田间尺度的颗粒产量变化，还能够捕捉作物田间生产力的异质性。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact of this Small Business Innovation Research (SBIR) Phase I project is to quantitatively assess farmland status and resilience. This project studies varying agricultural productivity subject to weather and static soil and landscape properties. This study will develop models using artificial intelligence to make predictions. It will be based on data from the U.S. and other agriculturally-intense regions of the world, allowing the generalization of the framework into new geographical domains. The models will also be tested on a variety of staple crops, such as corn, soybean, wheat, and rice.This system will include an interface for untrained users, as well as important data for quantitative financial analysis. This SBIR Phase I project aims to develop an integrative machine-learning framework consisting of state-of-the-art generative weather models, feature translation models, and crop yield models to obtain a rich ensemble of simulated growing season environmental conditions, and associated yield estimates. Supported by high-resolution satellite imagery in the past 20 years, the model is not only capable of capturing granular yield variability at the field scale, but also the heterogeneity of productivity within a crop field.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.