Due to the unfavorable soil conditions and water resources, the cropland use pattern in the farming-pastoral ecotone in northern China is complex. The program named "Grain for Green" has accelerated the cropland change. However, the complex cropland and retired cropland are challenging to monitor with remote sensing due to their spatially dispersed and easily confused with spectrally similar land use classes such as nature grasslands and non-cropped fields. Taking farming-pastoral ecotone in the northern foot of the Yinshan Mountains as a case study, we explored a classification approach for complex cropland and retired cropland, which was introduced as a specific land use class by using multi-temporal Landsat TM and OLI images with Google Earth Engine. During 1990-2000, cropland increased with a sharper growth and increased with a slower growth from 2001 to 2010, and then decreased significantly from 2011 to 2019, to lead the cropland area in 2019 was smaller than an area in 1990. We analyzed the spatiotemporal trajectories of retired cropland in 2019 using the Land Use Change Trajectory method to evaluate its source. In our finding, approximately 77% of retired cropland was labelled as cropland before 2019; albeit, not all retired cropland was converted from cropland. Moreover, we qualitatively assessed the vegetation dynamics in the study area by utilizing the long-term NDVI-mean value to reveal that vegetation coverage has shown a continuously increasing trend. It is related to the decline of cropland and the increase of retired cropland at the same rate. Our results highlighted that the "Grain for Green" program had led the vegetation restoration in the farming-pastoral ecotone. Our approach for monitoring cropland and retired cropland can improve the understanding of the driving factors and consequences of these critical land use change trajectories.

The cropland in the farming-pastoral ecotone of Northern China is highly unstable owing to environmental restoration projects, poor soil fertility, poverty, and rural labor loss, and it is characterized by a large number of fallow fields. Mapping fallow fields in a farming-pastoral ecotone can help in evaluating the impact of complex cropland landscapes on the environment and food security. To map the fallow fields using the Sentinel-1 and Sentinel-2 archives, a multi-metric dataset of vertical transmit–vertical receive + vertical transmit–horizontal receive polarization was established. Moreover, spectral bands and vegetation index datasets were established using Google Earth Engine to classify cropped and fallow fields using the Random Forest classifier. The overall accuracies and Kappa coefficients of different datasets were assessed to examine the dataset with the highest overall accuracy in the main growing season. A 10 m resolution fallow map for 2020 was then generated based on the combined Sentinel-1 and Sentinel-2 datasets with the highest overall accuracy and Kappa coefficients were 95.82% and 0.92, respectively. In addition, the time-series characteristics of the entropy eigenvalues generated via dual-polarization decomposition were quantitatively evaluated to clarify the contribution of the Sentinel-1 synthetic-aperture radar archive to the fallow field mapping. The eigenvalues were more sensitive to the phenological characteristics of cropped and fallow fields than the original backscatter signal of the Sentinel-1 data. Moreover, the mapping method was tested at different time intervals by gradually aggregating the results across an increasing number of months to optimize the fallow field monitoring using the minimum number of observations possible within a short period. Data aggregated over August achieved the highest one-month accuracy; it was also very close to the observations from the whole growing season. The results further emphasize the influence of Sentinel-1 archives on fallow field mapping. Overall, this study clarifies the potential applicability of Sentinel archives for monitoring and mapping managing patterns of agricultural land in a region.

Knowledge of grassland classification in a timely and accurate manner is essential for grassland resource management and utilization. Although remote sensing imagery analysis technology is widely applied for land cover classification, few studies have systematically compared the performance of commonly used methods on semi-arid native grasslands in northern China. This renders the grassland classification work in this region devoid of applicable technical references. In this study, the central Xilingol (China) was selected as the study area, and the performances of four widely used machine learning algorithms for mapping semi-arid grassland under pixel-based and object-based classification methods were compared: random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN), and naive Bayes (NB). The features were composed of the Landsat OLI multispectral data, spectral indices, Sentinel SAR C bands, topographic, position (coordinates), geometric, and grey-level co-occurrence matrix (GLCM) texture variables. The findings demonstrated that (1) the object-based methods depicted a more realistic land cover distribution and had greater accuracy than the pixel-based methods; (2) in the pixel-based classification, RF performed the best, with OA and Kappa values of 96.32% and 0.95, respectively. In object-based classification, RF and SVM presented no statistically different predictions, with OA and Kappa exceeding 97.5% and 0.97, respectively, and both performed significantly better than other algorithms. (3) In pixel-based classification, multispectral bands, spectral indices, and geographic features significantly distinguished grassland, whereas, in object-based classification, multispectral bands, spectral indices, elevation, and position features were more prominent. Despite the fact that Sentinel 1 SAR variables were chosen as an effective variable in object-based classification, they made no significant contribution to the grassland distinction.

The agricultural land use combined with agronomic management practices shall be structured on sustainable practices, guaranteeing both the maximization of productivity and environment preservation. NDVI (Normalized Difference Vegetation Index) time-series has been recognized as a useful methodology to monitor crop development and its spatial distribution. However, there is always a trade-off between spatial and temporal resolutions in satellite data. Hence, high spatial and temporal resolutions from Planet CubeSat represent a possibility to overcome this trade-off. This paper investigated the potential of using high spatial resolution daily NDVI-time-series from Planet CubeSat images for crop monitoring. One hundred nineteen images from 2017, at 3 m ground sampling distance, over cotton, spring corn and winter wheat fields, were acquired and converted into NDVI. The harmonic analysis of time series (HANTS) algorithm was applied to obtain a smoothed cloud and gap-free daily time-series. The 3 m daily time-series were resized to daily 9 and 30 m resolution; and resampled to temporal resolutions at 4, 8 and 16 days intervals to assess the impact of spatial and temporal resolution on NDVI time-series. NDVI time-series were evaluated by their minimum, maximum, average and coefficient of variation across the year. Principal component analysis (PCA) and the stepwise procedure were applied to assess optimum features (days across the year) to assist the NDVI-time-series interpretation. PCA and stepwise highlighted the best time across the year for NDVI-time-series interpretation. As the spatial resolution decreases, the range of NDVI and its standard deviation within field also decreases, leading to loss of within field spectral variability. At daily temporal resolution, slight differences in crop development can be detected in a very short time interval, but as the temporal resolution decreases the changes in crop development are detected at larger rates. The high temporal and spatial resolutions from Planet CubeSat images demonstrated great potential to monitor agricultural systems and can subsidize, on forthcoming research, the local and regional monitoring of agricultural areas and contribute to better management regarding strategic planning of governmental and corporate decision making over technical issues.

Amid growing global food security concerns and frequent armed conflicts, real-time monitoring of abandoned cropland is essential for strategic planning and crisis management. This study develops a method to map abandoned cropland accurately, crucial for maintaining the food supply chain and ecological balance. Utilizing Sentinel-1/2 satellite data, we employed multi-feature stacking and machine learning to create the ARCC10-IM (Abandoned and Reclaimed Cropland Classification at 10-meter resolution in Inner Mongolia) dataset, which tracks annual cropland activity. A novel temporal segmentation algorithm was developed to extract cropland abandonment and reclamation patterns annually, using sliding time windows over several years. This research differentiates cropland states—active cultivation, unstable fallowing, continuous abandonment, and reclamation—providing continuous, regional-scale maps with 10-meter resolution. ARCC10-IM is crucial for land planning, environmental monitoring, and agricultural management in arid areas like Inner Mongolia, enhancing decision-making and technology in land use tracking.