The management of crop residues in farmland is crucial for increasing soil organic matter and reducing soil erosion. Identifying the regional extent of crop residue cover (CRC) is vital for implementing conservation tillage and formulating agricultural subsidy policies. The Google Earth Engine (GEE) and remote sensing images from 2019 to 2023 were used to obtain spectral characteristics before the maize seedling stage in Northeast China, followed by constructing the CRC estimation models using machine learning algorithms. To avoid the impact of multicollinearity among data, three machine learning algorithms—ridge regression (RR), partial least squares regression (PLSR), and least absolute shrinkage and selection operator (LASSO)—were employed. By comparing the accuracy of these methods, the most accurate model was determined and applied to subsequent CRC estimation. Based on the estimated CRC and Conservation Technology Information Center definitions of tillage practices, the conservation tillage mapping was completed, and the spatiotemporal distribution characteristics were thoroughly analyzed. The following findings were demonstrated: (1) the PLSR-based model outperformed RR (Pearson’s correlation coefficient (r) = 0.8875, R² = 0.7877, RMSE = 6.99%) and LASSO (r = 0.8903, R² = 0.7926, RMSE = 6.88%) with higher accuracy (r = 0.9264, R² = 0.8582, RMSE = 4.93%). (2) Over the five years, the average no-tillage (NT) proportion in the study area was 15.9%, reduced tillage (RT) was 17.8%, and conventional tillage (CT) was 66.3%. In 2020 and 2022, NT rates were significantly higher at 27.5% and 15.5%, while RT were 15.7% and 30.0%, respectively. (3) Compared to the Sanjiang and Liaohe Plains (RT = 1907 km² and 1336 km², and NT = 559 km² and 585 km², respectively), the Songnen Plain exhibited higher conservation tillage rates (where RT was 3791 km² and NT was 1265 km²). This provides crucial scientific evidence for the management and planning of conservation tillage, thereby optimizing farmland production planning, enhancing production efficiency, and promoting the development of sustainable agricultural production systems.

Straw incorporation (SI) is a key strategy for promoting sustainable agriculture. It aims to mitigate environmental pollution caused by straw burning and enhances soil organic matter content, which increases crop yields. Consequently, the accurate and efficient monitoring of SI is crucial for promoting sustainable agricultural practices and effective management. In this study, we employed the Google Earth Engine (GEE) to analyze time-series Sentinel-2 data with the Mann–Kendall (MK) algorithm. This approach enabled the extraction and spatial distribution retrieval of SI regions in a representative household mode area in Northeast China. Among the eight tillage indices analyzed, the simple tillage index (STI) exhibited the highest inversion accuracy, with an overall accuracy (OA) of 0.85. Additionally, the bare soil index (BSI) achieved an overall accuracy of 0.84. In contrast, the OA of the remaining indices ranged from 0.28 to 0.47, which were significantly lower than those of the STI and BSI. This difference indicated the limited performance of the other indices in retrieving SI. The high accuracy of the STI is primarily attributed to its reliance on the bands B11 and B12, thereby avoiding potential interference from other spectral bands. The geostatistical analysis of the SI distribution revealed that the SI rate in the household mode area was 36.10% in 2022 in the household mode area. Regions A, B, C, and D exhibited SI rates of 34.76%, 33.05%, 57.88%, and 22.08%, respectively, with SI mainly concentrated in the eastern area of Gongzhuling City. Furthermore, the study investigated the potential impacts of household farming practices and national policies on the outcomes of SI implementation. Regarding state subsidies, the potential returns from SI per hectare of cropland in the study area varied from RMB −65 to 589. This variation indicates the importance of higher subsidies in motivating farmers to adopt SI practices. Sentinel-2 satellite imagery and the MK test were used to effectively monitor SI practices across a large area. Future studies will aim to integrate deep learning techniques to improve retrieval accuracy. Overall, this research presents a novel perspective and approach for monitoring SI practices and provides theoretical insights and data support to promote sustainable agriculture.

Remote sensing estimation of maize residue cover (MRC) can rapidly acquire large-scale data on MRC, crucial for monitoring and promoting conservation tillage. Herein, seven tillage indices derived from Sentinel-2 satellite imagery were analyzed alongside measured MRC data to assess their correlation with MRC. MRC estimation models were built using six machine learning algorithms, including back propagation neural network (BPNN), random forest (RF), support vector regression (SVR), extreme gradient boosting (XGBoost), Stacking1, and Stacking2. Model performance was compared using the coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE). The potential for conservation tillage was explored. The results showed that the R² values of the seven tillage indices in the study area exceeded 0.5, with particularly high correlations for NDTI and STI, with R² values of 0.755 and 0.751, respectively. When using machine learning algorithms to construct models, the Stacking2 model exhibited the highest estimation accuracy, with an R² of 0.923, RMSE of 3.32%, and MAE of 0.025, while Stacking1 also demonstrated robust performance, with an R² of 0.910, RMSE of 3.45%, and MAE of 0.029. Among the base models, XGBoost achieved the highest estimation performance and the lowest error, with R², RMSE, and MAE values of 0.884, 4.77%, and 0.031, respectively. The R² values of RF, SVR, and BPNN were 0.865, 0.859, and 0.842, respectively, with RMSE values of 4.06%, 4.76%, and 5.91%, and MAE values of 0.039, 0.047, and 0.059, respectively. These results indicate that the Stacking2 model demonstrates a significant advantage in prediction accuracy. Geostatistical analysis of the inversion results of the Stacking2 model revealed that the proportions of farmland with MRC values exceeding 30% in Changchun, Songyuan, and Siping were 81.90%, 77.96%, and 83.58%, respectively. This indicates that Changchun and Siping have greater potential for implementing conservation tillage. This study demonstrates that the stacking ensemble learning model significantly improves the predictive performance by leveraging the strengths of multiple base models and accurately monitoring the spatial distribution of MRC.

Employing remote sensing techniques to evaluate crop residue cover (CRC) enables rapid mapping of tillage practices over large cropland areas, which has significant practical implications for monitoring the implementation of conservation tillage practices. This research utilized Sentinel-2 MSI and Landsat-8 OLI remotely sensed data, various spectral indices were calculated and the datasets were correlated with the field-measured CRC data. Selected spectral indices, highly significantly correlated, were chosen to build a correlation model between the indices and the CRC. Considering Sentinel-2 MSI and Landsat 8 OLI remotely sensed data variations in spectral and spatial scales, the accuracy of CRC models was evaluated using R2 and RMSE values. From the results, it's evident that all six spectral indices, including STI, NDTI, SRNDR, NDI5, NDI7 and NDSVI, registered correlation coefficients with the CRC exceeded 0.3 in the study area. STI and NDTI showed a stronger correlation to CRC, with coefficients of 0.810 and 0.803, respectively. For the Landsat 8 data, the lowest correlation obtained was for NDSVI with the Landsat 8 data with a correlation coefficient of 0.358. Applying the linear regression technique, STI and NDTI obtained higher accuracy compared to other indices in the Sentinel-2 MSI data. For NDTI and STI, The R2 values were 0.650 and 0.665, respectively, while their corresponding RMSE values were 3.96% and 4.03%. The highest model accuracy was obtained for the STI and NDTI constructed from the Landsat 8 OLI data (R2 values 0.41 and 0.40; RMSE values 5.25% and 5.27%, respectively). The CRC model built using partial least squares regression (PLSR) exhibited greater precision when applied to the Sentinel-2 MSI data (R2 value 0.894; RMSE value 2.18%) in comparison to the Landsat 8 OLI data (R2 value 0.695; RMSE value 3.70%). PLSR has the potential to enhance the precision of the model. In addition, the study area shows that the estimation of the CRC is better in the one-dimensional linear regression model and the PLSR model created with the Sentinel-2 MSI optical data compared to the Landsat 8 OLI optical remotely sensed data. The validation suggests that the CRC estimation in the study area is more precise when using the model relying on Sentinel-2 satellite imagery rather than the Landsat 8 OLI imagery.

Saline–alkaline land serves as a potential arable land reserve for augmenting agricultural productivity and safeguarding food security. However, long-term monitoring of saline–alkaline land conversion remains challenging because of vegetation recovery, surface changes, hydrological modification, and agricultural phenology. Compared with CCDC and LandTrendr, the proposed MK-based framework detects conversion occurrence and timing while reducing dependence on dense observations, parameter tuning, and annual classification. This study examines the spatiotemporal dynamics of saline–alkaline land converted into paddies in Da’an City, utilizing Landsat time-series data (2007–2021) from the Google Earth Engine (GEE) platform. The analysis employed Mann–Kendall (MK) trend and mutation tests to monitor conversion processes and analyze spatiotemporal dynamics. Point-biserial correlation analysis was applied to evaluate the sensitivity of various remote sensing indices in detecting land conversion. The top fifteen indices, including the Land Surface Water Index (LSWI), Salinity Index 4 (SI4), and Salinity Index 5 (SI5), demonstrated strong correlations (|r| = 0.788–0.885) and significant pre- and post-conversion spectral differences (p < 0.01). Validation via confusion matrix confirmed that the June SI5 index attained the highest detection accuracy (overall accuracy: 94.15%; Kappa coefficient: 0.86), supporting the MK trend test’s efficacy in monitoring conversion processes. The MK mutation test achieved 80.36% temporal accuracy in determining conversion timing. The spatiotemporal analyses identified heterogeneity in saline–alkaline land conversion patterns. Spatially, large contiguous paddy fields dominated the eastern region, whereas fragmented conversion characterized the west, with minimal activity in the central zone. Temporally, the conversion area expanded rapidly before 2015 and then gradually declined, reaching a cumulative converted area of 276.29 km² by 2021. This study elucidates spatiotemporal conversion dynamics to guide sustainable land use.