The Forel-Ule Index (FUI) is an important parameter that can be calculated from optical remote sensing data to assess water quality based on water colour. Using Sentinel-2 images from April to November within the 2016–2020 period coupled with the Google Earth Engine Platform, we calculated FUI to analyse the spatial distribution, seasonal variations, and inter-annual variations of water colour in Baiyangdian Lake in the Xiong’an New Area established on 1 April 2017. The lake was divided into seven sub-regions, A–G; subsequently, high and low FUI values were observed in the south and north, respectively. Additionally, the mean FUI values of G and F zones in the south were 11.9 and 12.7, respectively, whereas those for the A, B, C, D, and E zones in the north were 10.5, 9.8, 10.4, 11.1, 11.2, respectively. The seasonal variations in the Baiyangdian Lake and seven sub-regions were consistent, with turbid water in spring and autumn, and clear water in summer. Inter-annual variations analyses for 2016–2020 indicated that the zone of A became progressively turbid, whereas the B, C, D, E, F, and G zones exhibited slow and gradually decreasing trends. Our findings suggest that the overall water quality of Baiyangdian Lake may be better, which may be related to the governance policies of the region.

As polluted water bodies are often small in area and widely distributed, performing artificial field screening is difficult; however, remote-sensing-based screening has the advantages of being rapid, large-scale, and dynamic. Polluted water bodies often show anomalous water colours, such as black, grey, and red. Therefore, the large-scale recognition of suspected polluted water bodies through high-resolution remote-sensing images and water colour can improve the screening efficiency and narrow the screening scope. However, few studies have been conducted on such kinds of water bodies. The hue angle of a water body is a parameter used to describe colour in the International Commission on Illumination (CIE) colour space. Based on the measured data, the water body with a hue angle greater than 230.958° is defined as a water colour anomaly, which is recognised based on the Sentinel-2 image through the threshold set in this study. The results showed that the hue angle of the water body was extracted from the Sentinel-2 image, and the accuracy of the hue angle calculated by the in situ remote-sensing reflectance R_rs (λ) was evaluated, where the root mean square error (RMSE) and mean relative error (MRE) were 4.397° and 1.744%, respectively, proving that this method is feasible. The hue angle was calculated for a water colour anomaly and a general water body in Qiqihar. The water body was regarded as a water colour anomaly when the hue angle was >230.958° and as a general water body when the hue angle was ≤230.958°. High-quality Sentinel-2 images of Qiqihar taken from May 2016 to August 2019 were chosen, and the position of the water body remained unchanged; there was no error or omission, and the hue angle of the water colour anomaly changed obviously, indicating that this method had good stability. Additionally, the method proposed is only suitable for optical deep water, not for optical shallow water. When this method was applied to Xiong’an New Area, the results showed good recognition accuracy, demonstrating good universality of this method. In this study, taking Qiqihar as an example, a surface survey experiment was conducted from October 14 to 15, 2018, and the measured data of six general and four anomalous water sample points were obtained, including water quality terms such as R_rs (λ), transparency, water colour, water temperature, and turbidity.

During the vegetation growing season, the forest in the remote sensing image is more distinguishable from other background features, and the forest features are obvious and can show prominent forest area characteristics. However, deep convolutional neural network-based methods tend to overlearn the forest features in the forest extraction task, which leads to the extraction speed still having a large amount of room for improvement. In this paper, a convolutional neural network-based model is proposed based on the incorporation of spatial and channel reconstruction convolution in the U-Net model for forest extraction from remote sensing images. The network obtained an extraction accuracy of 81.781% in intersection over union (IoU), 91.317% in precision, 92.177% in recall, and 91.745% in F1-score, with a maximum improvement of 0.442% in precision when compared with the classical U-Net network. In addition, the speed of the model’s forest extraction has been improved by about 6.14 times. On this basis, we constructed a forest land dataset with high-intraclass diversity and fine-grained scale by selecting some Sentinel-2 images in Northeast China. The spatial and temporal evolutionary changes of the forest cover in the Fuxin region of Liaoning province, China, from 2019 to 2023, were obtained using this region as the study area. In addition, we obtained the change of the forest landscape pattern evolution in the Fuxin region from 2019 to 2023 based on the morphological spatial pattern analysis (MSPA) method. The results show that the core area of the forest landscape in the Fuxin region has shown an increasing change, and the non-core area has been decreasing. The SC-UNet method proposed in this paper can realize the high-precision and rapid extraction of forest in a wide area, and at the same time, it can provide a basis for evaluating the effectiveness of ecosystem restoration projects.

As an important input parameter of the ecological network, the accuracy and detail with which forest cover is extracted directly constrain the accuracy of forest ecological network construction. The development of medium- and high-resolution remote sensing technology has provided an opportunity to obtain accurate and high-resolution forest coverage data. As forests have diverse contours and complex scenes on remote sensing images, a model of them will be disturbed by the natural distribution characteristics of complex forests, which in turn will affect the extraction accuracy. In this study, we first constructed a rather large, complex, diverse, and scene-rich forest extraction dataset based on Sentinel-2 multispectral images, comprising 20,962 labeled images with a spatial resolution of 10 m, in a manually and accurately labeled manner. At the same time, this paper proposes the Dynamic Large Kernel Segformer and conducts forest extraction experiments in Liaoning Province, China. We then used forest coverage as an input parameter and classified the forest landscape patterns in the study area using a landscape spatial pattern characterization method, based on which a forest ecological network was constructed. The results show that the Dynamic Large Kernel Segformer obtains 80.58% IoU, 89.29% precision, 88.63% recall, and a 88.96% F1 Score in extraction accuracy, which is 4.02% higher than that of the Segformer network, and achieves large-scale forest extraction in the study area. The forest area in Liaoning Province increased during the 5-year period from 2019 to 2023. With respect to the overall spatial pattern change, the Core area of Liaoning Province saw an increase in 2019–2023, and the overall quality of the forest landscape improved. Finally, we constructed the forest ecological network for Liaoning Province in 2023, which consists of ecological sources, ecological nodes, and ecological corridors based on circuit theory. This method can be used to extract large areas of forest based on remote sensing images, which is helpful for constructing forest ecological networks and achieving coordinated regional, ecological, and economic development.