Remote Sensing, Journal Year: 2024, Volume and Issue: 16(18), P. 3427 - 3427

Published: Sept. 15, 2024

Scientific evaluation of cultivated land quality (CLQ) is necessary for promoting rational utilization and achieving one the Sustainable Development Goals (SDGs): Zero Hunger. However, CLQ system proposed in previous studies was diversified, methods were inefficient. In this study, based on China’s first national standard “Cultivated Land Quality Grade” (GB/T 33469-2016), we constructed a unified county-level by selecting 15 indicators from five aspects—site condition, environmental physicochemical property, nutrient status field management—and used Delphi method to calculate membership degree indicators. Taking Jimo district Shandong Province, China, as case compared performance three machine learning models, including random forest, AdaBoost, support vector regression, evaluate using multi-temporal remote sensing data. The comprehensive index reveal spatial distribution CLQ. results showed that data model efficient reliable, had significant positive correlation with crop yield (r 0.44, p < 0.001). proportions high-, medium- poor-quality 27.43%, 59.37% 13.20%, respectively. western part study area better, while it worse eastern central parts. main limiting factors include irrigation capacity texture configuration. Accordingly, series targeted measures policies suggested, such strengthening construction farmland water conservancy facilities, deep tillage soil continuing construct well-facilitated farmland. This fast reliable evaluating CLQ, are helpful promote protection ensure food security.

Language: Английский