The use of remote sensing to monitor coastlines with wide distributions and dynamic changes is significant for coastal environmental monitoring and resource management. However, most current remote sensing information extraction of coastlines is based on the instantaneous waterline, which is obtained by single-period imagery. The lack of a unified standard is not conducive to the dynamic change monitoring of a changeable coastline. The tidal range observation correction method can be used to correct coastline observation to a unified climax line, but it is difficult to apply on a large scale because of the distribution of observation sites. Therefore, we proposed a coastline extraction method based on the remote sensing big data platform Google Earth Engine and dense time-series remote sensing images. Through the instantaneous coastline probability calculation system, the coastline information could be extracted without the tidal range observation data to achieve a unified tide level standard. We took the Malay Islands as the experimental area and analyzed the consistency between the extraction results and the existing high-precision coastline thematic products of the same period to achieve authenticity verification. Our results showed that the coastline data deviated 10 m in proportion to a reach of 40% and deviated 50 m within a reach of 89%. The overall accuracy was kept within 100 m. In addition, we extracted 96 additional islands that have not been included in public data. The obtained multi-phase coastlines showed the spatial distribution of the changing hot regions of the Malay Islands’ coastline, which greatly supported our analysis of the reasons for the expansion and retreat of the coastline in this region. These research results showed that the big data platform and intensive time-series method have considerable potential in large-scale monitoring of coastline dynamic change and island reef change monitoring.

A flood is a common and highly destructive natural disaster. Recently, machine learning methods have been widely used in flood susceptibility analysis. This paper proposes a NHAND (New Height Above the Nearest Drainage) model as a framework to evaluate the effectiveness of both individual learners and ensemble models in addressing intricate flood-related challenges. The evaluation process encompasses critical dimensions such as prediction accuracy, model training duration, and stability. Research findings reveal that, compared to Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Lasso, Random Forest (RF), and Extreme Gradient Boosting (XGBoost), Stacked Generalization (Stacking) outperforms in terms of predictive accuracy and stability. Meanwhile, XGBoost exhibits notable efficiency in terms of training duration. Additionally, the Shapley Additive Explanations (SHAP) method is employed to explain the predictions made by the XGBoost.

Timely and accurate rice spatial distribution maps play a vital role in food security and social stability. Early-season rice mapping is of great significance for yield estimation, crop insurance, and national food policymaking. Taking Tongjiang City in Heilongjiang Province with strong spatial heterogeneity as study area, a hierarchical K-Means binary automatic rice classification method based on phenological feature optimization (PFO-HKMAR) is proposed, using Google Earth Engine platform and Sentinel-1/2, and Landsat 7/8 data. First, a SAR backscattering intensity time series is reconstructed and used to construct and optimize polarization characteristics. A new SAR index named VH-sum is built, which is defined as the summation of VH backscattering intensity for specific time periods based on the temporal changes in VH polarization characteristics of different land cover types. Then comes feature selection, optimization, and reconstruction of optical data. Finally, the PFO-HKMAR classification method is established based on Simple Non-Iterative Clustering. PFO-HKMAR can achieve early-season rice mapping one month before harvest, with overall accuracy, Kappa, and F1 score reaching 0.9114, 0.8240 and 0.9120, respectively (F1 score is greater than 0.9). Compared with the two crop distribution datasets in Northeast China and ARM-SARFS, overall accuracy, Kappa, and F1 scores of PFO-HKMAR are improved by 0.0507–0.1957, 0.1029–0.3945, and 0.0611–0.1791, respectively. The results show that PFO-HKMAR can be promoted in Northeast China to enable early-season rice mapping, and provide valuable and timely information to different stakeholders and decision makers.