The prediction of soil organic matter is important for measuring the soil’s environmental quality and the degree of degradation. In this study, we combined China’s GF-6 remote sensing data with the organic matter content data obtained from soil sampling points in the study area to predict soil organic matter content. To these data, we applied the random forest (RF), light gradient boosting machine (LightGBM), gradient boosting tree (GBDT), and extreme boosting machine (XGBoost) learning models. We used the coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) to evaluate the prediction model. The results showed that XGBoost (R2 = 0.634), LightGBM (R2 = 0.627), and GBDT (R2 = 0.591) had better accuracy and faster computing time than that of RF (R2 = 0.551) during training. The regression model established by the XGBoost algorithm on the feature-optimized anthrosols dataset had the best accuracy, with an R2 of 0.771. The inversion of soil organic matter content based on GF-6 data combined with the XGBoost model has good application potential.

We studied the influence and correlation of soil improvement, farmland ecological protection, soil fertilization, and field infrastructure construction on the quality grade of well-fertilized farmland in the engineering measures of well-fertilized farmland construction. Taking Xiao County of the Anhui Province as the study area, based on the software platforms of SPSS, ArcGIS10.6, and the county farmland resource management information system, we investigated the farmland quality changes of well-facilitated farmland before and after construction using the fuzzy evaluation method and analytic hierarchy process. We used principal component analysis and the gray relational method to analyze the impact and correlation of various engineering measures on farmland quality. The farmland quality grade in the study area was improved by a 0.59 grade after the construction of the well-facilitated farmland. Well-facilitated farmland construction engineering measures mainly affected the farmland quality through 12 factors, such as the soil bulk density, tillage layer texture, irrigation and drainage guarantee rates, forest network density, and field road accessibility. There is a strong correlation between these factors and the characteristics of farmland quality; the degrees of correlation were 0.865–0.610, respectively. The highest correlation degree was 0.939 between the deep plowing and deep loosening soil improvement project and the improvement of the well-facilitated basic farmland quality; this was followed by soil fertilization with an increased application of organic fertilizer, farmland ecological protection, and the field infrastructure project with correlations of 0.936, 0.857, and 0.563, respectively. Represented by the improvement of farmland fertility, the soil improvement project had the strongest impact on well-facilitated farmland quality. The soil fertility project, farmland ecological protection project, and the field infrastructure project were the second most important, with very close degrees of correlation.