Exploiting time series of Sentinel-1 and Sentinel-2 to detect grassland mowing events using deep learning with reject region

Identification of Typical Ecosystem Types by Integrating Active and Passive Time Series Data of the Guangdong-Hong Kong-Macao Greater Bay Area, China

The identification of ecosystem types is important in ecological environmental assessment. However, due to cloud and rain and complex land cover characteristics, commonly used ecosystem identification methods have always lacked accuracy in subtropical urban agglomerations. In this study, China's Guangdong-Hong Kong-Macao Greater Bay Area (GBA) was taken as a study area, and the Sentinel-1 and Sentinel-2 data were used as the fusion of active and passive remote sensing data with time series data to distinguish typical ecosystem types in subtropical urban agglomerations. Our results showed the following: (1) The importance of different features varies widely in different types of ecosystems. For grassland and arable land, two specific texture features (VV_dvar and VH_diss) are most important; in forest and mangrove areas, synthetic-aperture radar (SAR) data for the months of October and September are most important. (2) The use of active time series remote sensing data can significantly improve the classification accuracy by 3.33%, while passive time series remote sensing data improves by 4.76%. When they are integrated, accuracy is further improved, reaching a level of 84.29%. (3) Time series passive data (NDVI) serve best to distinguish grassland from arable land, while time series active data (SAR data) are best able to distinguish mangrove from forest. The integration of active and passive time series data also improves precision in distinguishing vegetation ecosystem types, such as forest, mangrove, arable land, and, especially, grassland, where the accuracy increased by 21.88%. By obtaining real-time and more accurate land cover type change information, this study could better serve regional change detection and ecosystem service function assessment at different scales, thereby supporting decision makers in urban agglomerations.

The Influence of Data Density and Integration on Forest Canopy Cover Mapping Using Sentinel-1 and Sentinel-2 Time Series in Mediterranean Oak Forests

Forest canopy cover (FCC) is one of the most important forest inventory parameters and plays a critical role in evaluating forest functions. This study examines the potential of integrating Sentinel-1 (S-1) and Sentinel-2 (S-2) data to map FCC in the heterogeneous Mediterranean oak forests of western Iran in different data densities (one-year datasets vs. three-year datasets). This study used very high-resolution satellite images from Google Earth, gridded points, and field inventory plots to generate a reference dataset. Based on it, four FCC classes were defined, namely non-forest, sparse forest (FCC = 1–30%), medium-density forest (FCC = 31–60%), and dense forest (FCC > 60%). In this study, three machine learning (ML) models, including Random Forest (RF), Support Vector Machine (SVM), and Classification and Regression Tree (CART), were used in the Google Earth Engine and their performance was compared for classification. Results showed that the SVM produced the highest accuracy on FCC mapping. The three-year time series increased the ability of all ML models to classify FCC classes, in particular the sparse forest class, which was not distinguished well by the one-year dataset. Class-level accuracy assessment results showed a remarkable increase in F-1 scores for sparse forest classification by integrating S-1 and S-2 (10.4% to 18.2% increased for the CART and SVM ML models, respectively). In conclusion, the synergetic use of S-1 and S-2 spectral temporal metrics improved the classification accuracy compared to that obtained using only S-2. The study relied on open data and freely available tools and can be integrated into national monitoring systems of FCC in Mediterranean oak forests of Iran and neighboring countries with similar forest attributes.