Yihan Ma

Due to an oversight on behalf of the author, the affiliation of the first author was inadvertently omitted from the original publication

In the field of smart agriculture, soil property data at the field scale drives the precision decision-making of agricultural inputs such as seeds and chemical fertilizers. However, soil texture has significant spatial variability at the field scale, and traditional remote sensing monitoring methods have certain data intermittency, which limits small-scale prediction research. In this study, based on the Google Earth Engine platform, soil synthetic images were generated according to different time intervals using mean compositing and median compositing modes, image bands were extracted, and spectral indices were introduced; combined with the random forest algorithm, the effects of different compositing time windows, compositing modes, and compositing data types on prediction accuracy were evaluated; and three partitioning strategies based on crop growth, soil synthetic image brightness, and soil type were adopted to conduct local partitioning regression of soil texture. The results show that: (1) The use of mean compositing of multi-year May images from 2021 to 2024 can improve prediction accuracy. When this method is combined with the “band reflectance + spectral indices” dataset, compared with other compositing methods, the R² of clay particles, silt particles, and sand particles can be increased by 8.89%, 9.50%, and 2.48% on average. (2) Compared with using only image band data, the introduction of spectral indices can significantly improve the prediction accuracy of soil texture at the field scale, and the R² of clay particles, silt particles, and sand particles is increased by 4.58%, 3.43%, and 4.59% on average, respectively. (3) Global regression is superior to local partitioning regression; however, the local partitioning regression strategy based on soil type has good accuracy performance. Under the optimal compositing method, the average R² of soil particles of each size fraction is only 1.08% lower than that of global regression, which has great application potential. This study innovatively constructs a comprehensive strategy of “moisture spectral indices + specific compositing time window + specific compositing mode + soil type partitioning”, providing a new paradigm for soil texture prediction at the field scale in Northeastern China, and lays the foundation for data-driven water and fertilizer decision-making.

Soil available nitrogen (AN) is a critical nutrient for plant absorption and utilization. Accurately mapping its spatial distribution is essential for improving crop yields and advancing precision agriculture. In this study, 188 AN soil samples (0–20 cm) were collected at Heshan Farm, Nenjiang County, Heihe City, Heilongjiang Province, in 2023. The soil available nitrogen content ranged from 65.81 to 387.10 mg kg⁻¹, with a mean value of 213.85 ± 61.16 mg kg⁻¹. Sentinel-2 images and normalized vegetation index (NDVI) and enhanced vegetation index (EVI) time series data were acquired on the Google Earth Engine (GEE) platform in the study area during the bare soil period (April, May, and October) and the growth period (June–September). These remote sensing variables were combined with soil sample data, crop type information, and crop growth period data as predictive factors and input into a Random Forest (RF) model optimized using the Optuna hyperparameter tuning algorithm. The accuracy of different strategies was evaluated using 5-fold cross-validation. The research results indicate that (1) the introduction of growth information at different growth periods of soybean and maize has different effects on the accuracy of soil AN mapping. In soybean plantations, the introduction of EVI data during the pod setting period increased the mapping accuracy R² by 0.024–0.088 compared to other growth periods. In maize plantations, the introduction of EVI data during the grouting period increased R² by 0.004–0.033 compared to other growth periods, which is closely related to the nitrogen absorption intensity and spectral response characteristics during the reproductive growth period of crops. (2) Combining the crop types and their optimal period growth information could improve the mapping accuracy, compared with only using the bare soil period image (R² = 0.597)—the R² increased by 0.035, the root mean square error (RMSE) decreased by 0.504%, and the mapping accuracy of R² could be up to 0.632. (3) The mapping accuracy of the bare soil period image differed significantly among different months, with a higher mapping accuracy for the spring data than the fall, the R² value improved by 0.106 and 0.100 compared with that of the fall, and the month of April was the optimal window period of the bare soil period in the present study area. The study shows that when mapping the soil AN content in arable land, different crop types, data collection time, and crop growth differences should be considered comprehensively, and the combination of specific crop types and their optimal period growth information has a greater potential to improve the accuracy of mapping soil AN content. This method not only opens up a new technological path to improve the accuracy of remote sensing mapping of soil attributes but also lays a solid foundation for the research and development of precision agriculture and sustainability.

During rice cultivation, extracting levees helps to delineate effective planting areas, thereby enhancing the precision of management zones. This approach is crucial for devising more efficient water field management strategies and has significant implications for water-saving irrigation and fertilizer optimization in rice production. The uneven distribution and lack of standardization of levees pose significant challenges for their accurate extraction. However, recent advancements in remote sensing and deep learning technologies have provided viable solutions. In this study, Youyi Farm in Shuangyashan City, Heilongjiang Province, was chosen as the experimental site. We developed the SCA-UNet model by optimizing the UNet algorithm and enhancing its network architecture through the integration of the Convolutional Block Attention Module (CBAM) and Squeeze-and-Excitation Networks (SE). The SCA-UNet model leverages the channel attention strengths of SE while incorporating CBAM to emphasize spatial information. Through a dual-attention collaborative mechanism, the model achieves a synergistic perception of the linear features and boundary information of levees, thereby significantly improving the accuracy of levee extraction. The experimental results demonstrate that the proposed SCA-UNet model and its additional modules offer substantial performance advantages. Our algorithm outperforms existing methods in both computational efficiency and precision. Significance analysis revealed that our method achieved overall accuracy (OA) and F1-score values of 88.4% and 90.6%, respectively. These results validate the efficacy of the multimodal dataset in addressing the issue of ambiguous levee boundaries. Additionally, ablation experiments using 10-fold cross-validation confirmed the effectiveness of the proposed SCA-UNet method. This approach provides a robust technical solution for levee extraction and has the potential to significantly advance precision agriculture.

Soil, a crucial natural resource and the cornerstone of agriculture, profoundly impacts crop growth, quality, and yield. However, soil degradation affects over one-third of global land, with topsoil loss emerging as a significant form of this degradation, posing a grave threat to agricultural sustainability and socio-economic development. Therefore, accurate monitoring of topsoil-loss distribution is essential for formulating effective soil protection and management strategies. Traditional survey methods are limited by time-consuming and labor-intensive processes, high costs, and complex data processing. These limitations make it particularly challenging to meet the demands of large-scale research and efficient information processing. Therefore, it is imperative to develop a more efficient and accurate extraction method. This study focuses on the Heshan Farm in Heilongjiang Province, China, as the research subject and utilizes remote sensing technology and machine learning methods. It introduces multi-source data, including Sentinel-2 satellite imagery and Digital Elevation Model (DEM) data, to design four extraction schemes. (1) spectral feature extraction; (2) spectral feature + topographic feature extraction; (3) spectral feature + index extraction; (4) spectral feature + topographic feature + index extraction. Models for topsoil loss identification based on Random Forest (RF) and Support Vector Machine (SVM) algorithms are developed, and the Particle Swarm Optimization (PSO) algorithm is introduced to optimize the models. The performance of the models is evaluated using overall accuracy and Kappa coefficient indicators. The results show that Scheme 4, which integrates spectral features, topographic features, and various indices, performs the best in extraction effects. The RF model demonstrates higher classification accuracy than the SVM model. The optimized PSO-RF and PSO-SVM models show significant improvements in extraction accuracy, especially the PSO-RF model, with an overall accuracy of 0.97 and a Kappa coefficient of 0.94. The PSO-RF model using Scheme 4 improves OA by 34.72% and Kappa by 38.81% compared to the RF model in Scheme 1. Topsoil loss has a significant negative impact on crop growth, severely restricting the normal growth and development of crops. This study provides an efficient technical means for monitoring soil degradation in black-soil regions and offers a scientific basis for formulating effective agricultural ecological protection strategies, thereby promoting the sustainable management of soil resources.