Mapping annual 10-m maize cropland changes in China during 2017-2021

Dynamic evolution characteristics and hazard assessment of compound drought/waterlogging and low temperature events for maize

Hazard assessment is fundamental in the field of disaster risk management. With the increase in global warming, compound water and temperature events have become more frequent. Current research lacks risk assessments of low temperatures and their compound events, necessitating relevant hazard assessment work to improve the accuracy and diversity of maize disaster prevention and mitigation strategies. This study comparatively analyzed the dynamic evolution characteristics and hazards of compound drought/waterlogging and low temperature events (CDLEs and CWLEs) for maize in the Songliao Plain during different growth periods from 1981 to 2020. First, composite drought/waterlogging and low temperature magnitude indices (CDLMI and CWLMI) were constructed to quantify the intensity of CDLEs and CWLEs by fitting non-exceedance probabilities. Next, static and dynamic hazard assessment models were developed by fitting probability density and cumulative probability density curves to CDLMI and CWLMI. The results showed that the correlations between SPRI and LTI across different decades were mainly negative during the three growth periods. The hazard ratings for both CDLEs and CWLEs were relatively high in the northern part of the study area, consistent with the higher occurrence, duration, and severity of both CDLEs and CWLEs at higher latitudes. Relative to 2001-2010, the center of gravity of hazard shifted southward for CDLEs and northward for CWLEs in 2011-2020. The mean duration, frequency, and hazard were generally higher for CWLEs, but CDLEs were associated with more severe maize yield reductions. This study provides new insights into compound disaster risk assessment, and the research methodology can be generalized to other agricultural growing areas to promote sustainable development of agricultural systems and food security.

Mapping annual 10-m soybean cropland with spatiotemporal sample migration

China, as the world's biggest soybean importer and fourth-largest producer, needs accurate mapping of its planting areas for global food supply stability. The challenge lies in gathering and collating ground survey data for different crops. We proposed a spatiotemporal migration method leveraging vegetation indices' temporal characteristics. This method uses a feature space of six integrals from the crops' phenological curves and a concavity-convexity index to distinguish soybean and non-soybean samples in cropland. Using a limited number of actual samples and our method, we extracted features from optical time-series images throughout the soybean growing season. The cloud and rain-affected data were supplemented with SAR data. We then used the random forest algorithm for classification. Consequently, we developed the 10-meter resolution ChinaSoybean10 maps for the ten primary soybean-producing provinces from 2019 to 2022. The map showed an overall accuracy of about 93%, aligning significantly with the statistical yearbook data, confirming its reliability. This research aids soybean growth monitoring, yield estimation, strategy development, resource management, and food scarcity mitigation, and promotes sustainable agriculture.

A two-branch cloud detection algorithm based on the fusion of a feature enhancement module and Gaussian mixture model

Accurate cloud detection is an important step to improve the utilization rate of remote sensing (RS). However, existing cloud detection algorithms have difficulty in identifying edge clouds and broken clouds. Therefore, based on the channel data of the Himawari-8 satellite, this work proposes a method that combines the feature enhancement module with the Gaussian mixture model (GMM). First, statistical analysis using the probability density functions (PDFs) of spectral data from clouds and underlying surface pixels was conducted, selecting cluster features suitable for daytime and nighttime. Then, in this work, the Laplacian operator is introduced to enhance the spectral features of cloud edges and broken clouds. Additionally, enhanced spectral features are input into the debugged GMM model for cloud detection. Validation against visual interpretation shows promising consistency, with the proposed algorithm outperforming other methods such as RF, KNN and GMM in accuracy metrics, demonstrating its potential for high-precision cloud detection in RS images.