Search

• GF-1 and GF-6 remote sensing data have potential for wetland change detection. • Spatial-temporal attention method can identify information changes in cultivated land to wetland areas. • Sanjiang National Nature Reserve has large wetland restoration areas located near water sources. • The results of the study have important implications for the restoration and sustainable development of wetlands. Wetlands are important ecosystems, and detecting changes in wetlands plays a very important role in the management of wetland resources. Therefore, we selected Sanjiang National Nature Reserve as the study area and proposed a method in which bi-temporal GaoFen (GF) remote sensing data was combined with a spatial–temporal attention neural network (STANet) model, coupled with the selection of spectral variables. We used the bi-temporal images from GF-1 and GF-6 and compared three band selection methods, Relief F, principal component analysis, and RGB combination, and two STANet-based change detection methods (BAM: basic spatial–temporal attention module and PAM: pyramid spatial–temporal attention module) to improve the change detection of the wetland restoration. The results show that the accuracy of wetland change detection is related to different combinations of spectral variable selection and STANet models. The combination of Relief F feature selection and the BAM model led to the highest accuracy of the wetland change detection, 71.72 % for F1-Score and 76.92 % for MIou. The vector results of the change detection statistics show that the area of the Sanjiang National Nature Reserve cultivated lands converted to wetlands is 46.05 km2. This study implies that the STANet method has the capacity of detecting complex wetland restoration. Red, Bule, NIR and Red Edge1 bands of GaoFen data can provide effective information in the detection of changes in wetlands. The results of the study can be used as a reference for rational planning of wetland restoration, seeking a balance between cultivated lands and wetlands, which is important for the sustainable development of wetland. [ABSTRACT FROM AUTHOR]

Accurate measurement of forest growing stem volume (GSV) is important for forest resource management and ecosystem dynamics monitoring. Optical remote sensing imagery has great application prospects in forest GSV estimation on regional and global scales as it is easily accessible, has a wide coverage, and mature technology. However, their application is limited by cloud coverage, data stripes, atmospheric effects, and satellite sensor errors. Combining multi-sensor data can reduce such limitations as it increases the data availability, but also causes the multi-dimensional problem that increases the difficulty of feature selection. In this study, GaoFen-2 (GF-2) and Sentinel-2 images were integrated, and feature variables and data scenarios were derived by a proposed adaptive feature variable combination optimization (AFCO) program for estimating the GSV of coniferous plantations. The AFCO algorithm was compared to four traditional feature variable selection methods, namely, random forest (RF), stepwise random forest (SRF), fast iterative feature selection method for k-nearest neighbors (KNN-FIFS), and the feature variable screening and combination optimization procedure based on the distance correlation coefficient and k-nearest neighbors (DC-FSCK). The comparison indicated that the AFCO program not only considered the combination effect of feature variables, but also optimized the selection of the first feature variable, error threshold, and selection of the estimation model. Furthermore, we selected feature variables from three datasets (GF-2, Sentinel-2, and the integrated data) following the AFCO and four other feature selection methods and used the k-nearest neighbors (KNN) and random forest regression (RFR) to estimate the GSV of coniferous plantations in northern China. The results indicated that the integrated data improved the GSV estimation accuracy of coniferous plantations, with relative root mean square errors (RMSErs) of 15.0% and 19.6%, which were lower than those of GF-2 and Sentinel-2 data, respectively. In particular, the texture feature variables derived from GF-2 red band image have a significant impact on GSV estimation performance of the integrated dataset. For most data scenarios, the AFCO algorithm gained more accurate GSV estimates, as the RMSErs were 30.0%, 23.7%, 17.7%, and 17.5% lower than those of RF, SRF, KNN-FIFS, and DC-FSCK, respectively. The GSV distribution map obtained by the AFCO method and RFR model matched the field observations well. This study provides some insight into the application of optical images, optimization of the feature variable combination, and modeling algorithm selection for estimating the GSV of coniferous plantations. [ABSTRACT FROM AUTHOR]