Research

19 pages, 5098 KiB

Open AccessArticle

Using Ensemble Learning for Remote Sensing Inversion of Water Quality Parameters in Poyang Lake

by Changchun Peng, Zhijun Xie and Xing Jin

Sustainability 2024, 16(8), 3355; https://doi.org/10.3390/su16083355 - 17 Apr 2024

Viewed by 311

Inland bodies of water, such as lakes, play a crucial role in sustaining life and supporting ecosystems. However, with the rapid development of socio-economics, water resources are facing serious pollution problems, such as the eutrophication of water bodies and degradation of wetlands. Therefore, [...] Read more.

Inland bodies of water, such as lakes, play a crucial role in sustaining life and supporting ecosystems. However, with the rapid development of socio-economics, water resources are facing serious pollution problems, such as the eutrophication of water bodies and degradation of wetlands. Therefore, the monitoring, management, and protection of inland water resources are particularly important. In past research, empirical models and machine learning models have been widely used for the water quality assessment of inland lakes. Due to the complexity of the optical properties of inland lake water bodies, the performance of these models is often limited. To overcome the limitations of these models, this study uses in situ water quality data from 2017 to 2018 and multispectral (MS) remote sensing data from Sentinel-2 to construct experimental samples of Poyang Lake. Based on these experimental samples, we constructed a spatio-temporal ensemble model (STE) to evaluate four common water quality parameters: chlorophyll-a (Chl-a), total phosphorus (TP), total nitrogen (TN), and chemical oxygen demand (COD). The model adopts an ensemble learning strategy, improving the model’s performance by merging multiple advanced machine learning algorithms. We introduced several indices related to water quality parameters as auxiliary variables, such as NDCI and Enhanced Three, and used band data and these auxiliary variables as predictive variables, thereby greatly enhancing the predictive potential of the model.The results show that the inversion accuracy of these four inversion models is high (

R^{2}

of 0.94, 0.88, 0.92, and 0.93; RMSE of 1.15, 0.01, 0.02, and 0.02; MAE of 0.81, 0.01, 0.09, and 0.10), indicating that the STE model has good evaluation accuracy. Meanwhile, we used the STE model to reveal the spatio-temporal distribution of Chl-a, TP, TN, and COD from 2017 to 2018, and analyzed their seasonal and spatial variation rules. The results of this study not only provide an effective and practical method for monitoring and managing water quality parameters in inland lakes, but also provide water security for socio-economic and ecological environmental safety. Full article

(This article belongs to the Special Issue Innovation and Sustainable Development of Remote Sensing Technology)

► Show Figures

Figure 1

19 pages, 2559 KiB

Open AccessArticle

Can Grassroots Governments’ Environmental Attention Effectively Improve Air Pollution? Empirical Evidence from Satellite Remote Sensing Technology

by Kai Lin, Yanli Shi and Hong Xu

Sustainability 2023, 15(21), 15309; https://doi.org/10.3390/su152115309 - 26 Oct 2023

Cited by 1 | Viewed by 779

Abstract

Air pollution poses a global challenge, prompting governments worldwide to implement environmental policies aimed at its mitigation. However, grassroots management is key to the effectiveness of pollution management. Traditional air monitoring, ranging from a specific point to broader areas, has inherent limitations. In [...] Read more.

Air pollution poses a global challenge, prompting governments worldwide to implement environmental policies aimed at its mitigation. However, grassroots management is key to the effectiveness of pollution management. Traditional air monitoring, ranging from a specific point to broader areas, has inherent limitations. In contrast, satellite remote sensing technology offers extensive spatial and temporal coverage, enabling real-time monitoring of data transmission. Can the amalgamation of grassroots governance and satellite remote sensing technology significantly enhance air pollution control? This article leverages satellite remote sensing data and county-level economic and social data from China spanning the period 2008 to 2019 to empirically explore the impact and mechanism of government environmental constraints on air pollution in grassroots areas. The following results were found: (1) Grassroots government environmental constraints exert a significant inhibitory effect on air pollution, and this conclusion remains valid after a series of robustness tests. (2) Mechanism tests reveal that grassroots government environmental constraints reduce county-level air pollution by fostering urbanization, enhancing industrial structures, and promoting innovation in green technologies. (3) There exists heterogeneity in the inhibitory effect of grassroots environmental constraints on air pollution, with a more pronounced impact in areas focusing on environmental protection, facing no economic constraints, large-scale, and located in central and western regions. The green governance awareness of a higher-level government shows an interaction effect on the reduction in environmental constraints at the grassroots government level, collectively contributing to the decrease in regional air pollution. The conclusion of this article underscores the vital role of satellite remote sensing technology in pollution control and provides insights into the direction of environmental regulation. Full article

(This article belongs to the Special Issue Innovation and Sustainable Development of Remote Sensing Technology)

► Show Figures

Figure 1

29 pages, 25112 KiB

Open AccessArticle

Landslide Susceptibility Mapping Based on Multitemporal Remote Sensing Image Change Detection and Multiexponential Band Math

by Xianyu Yu, Yang Xia, Jianguo Zhou and Weiwei Jiang

Sustainability 2023, 15(3), 2226; https://doi.org/10.3390/su15032226 - 25 Jan 2023

Cited by 5 | Viewed by 1618 | Correction

Abstract

Landslides pose a great threat to the safety of people’s lives and property within disaster areas. In this study, the Zigui to Badong section of the Three Gorges Reservoir is used as the study area, and the land use (LU), land use change [...] Read more.

Landslides pose a great threat to the safety of people’s lives and property within disaster areas. In this study, the Zigui to Badong section of the Three Gorges Reservoir is used as the study area, and the land use (LU), land use change (LUC) and band math (band) factors from 2016–2020 along with six selected commonly used factors are used to form a land use factor combination (LUFC), land use change factor combination (LUCFC) and band math factor combination (BMFC). An artificial neural network (ANN), a support vector machine (SVM) and a convolutional neural network (CNN) are chosen as the three models for landslide susceptibility mapping (LSM). The results show that the BMFC is generally better than the LUFC and the LUCFC. For the validation set, the highest simple ranking scores for the three models were obtained for the BMFC (37.2, 32.8 and 39.2), followed by the LUFC (28, 26.6 and 31.8) and the LUCFC (26.8, 28.6 and 20); that is, the band-based predictions are better than those based on the LU and LUC, and the CNN model provides the best prediction ability. According to the four groups of experimental results with ANNs, compared with LU and LUC, band is easier to access, yields higher predictive performance, and provides stronger stability. Thus, band can replace LU and LUC to a certain extent and provide support for automatic and real-time landslide monitoring. Full article

(This article belongs to the Special Issue Innovation and Sustainable Development of Remote Sensing Technology)

► Show Figures

Figure 1

19 pages, 1157 KiB

Open AccessArticle

Impact of Carbon Sequestration by Terrestrial Vegetation on Economic Growth: Evidence from Chinese County Satellite Data

by Zuoming Zhang, Xiaoying Wan, Kaixi Sheng, Hanyue Sun, Lei Jia and Jiachao Peng

Sustainability 2023, 15(2), 1369; https://doi.org/10.3390/su15021369 - 11 Jan 2023

Cited by 6 | Viewed by 1653

Abstract

Land vegetation plays an important role in reducing greenhouse gas emissions and stabilizing atmospheric CO₂ concentration. However, the impact of carbon sequestration of terrestrial vegetation on economic growth has not yet been reported in the literature, especially in the context of China’s [...] Read more.

Land vegetation plays an important role in reducing greenhouse gas emissions and stabilizing atmospheric CO₂ concentration. However, the impact of carbon sequestration of terrestrial vegetation on economic growth has not yet been reported in the literature, especially in the context of China’s current high-quality economic development strategy, and clarifying carbon sequestration on high-quality economic development has an important research-support role in achieving the goal of “carbon peak” and “carbon neutral”. Therefore, based on the panel data from 2735 countries and cities in China from 2000 to 2017, this statistical analysis adopts a dual-fixed-effect model to identify the heterogeneous impacts of land-based vegetation carbon sequestration on high-quality urban economic development. The results show that carbon sequestration by terrestrial vegetation has a significant positive impact on economic growth in northeast, central, south, and southwest China but not in north, east, or northwest China, and after a series of stability tests, the effect still holds. Terrestrial vegetation carbon sequestration affects economic growth mainly through upgrades of industrial structures, resource allocation effect, and vegetation coverage. This statistical model further clarifies the empirical evidence provided by vegetation carbon sequestration for high-quality economic development and the economic effects on afforestation and ecological conservation. Full article

(This article belongs to the Special Issue Innovation and Sustainable Development of Remote Sensing Technology)

► Show Figures

Figure 1

26 pages, 11323 KiB

Open AccessArticle

Comparative Assessment of the Efficacy of the Five Kinds of Models in Landslide Susceptibility Map for Factor Screening: A Case Study at Zigui-Badong in the Three Gorges Reservoir Area, China

by Xianyu Yu, Tingting Xiong, Weiwei Jiang and Jianguo Zhou

Sustainability 2023, 15(1), 800; https://doi.org/10.3390/su15010800 - 01 Jan 2023

Cited by 3 | Viewed by 1935

Abstract

Landslides are geological disasters affected by a variety of factors that have the characteristics of a strong destructive nature and rapid development and cause major harm to the safety of people’s lives and property within the scope of the disaster. Excessive landslide susceptibility [...] Read more.

Landslides are geological disasters affected by a variety of factors that have the characteristics of a strong destructive nature and rapid development and cause major harm to the safety of people’s lives and property within the scope of the disaster. Excessive landslide susceptibility mapping (LSM) factors can reduce the accuracy of LSM results and are not conducive to researchers finding the key LSM factors. In this study, with the Three Gorges Reservoir area to the Padang section as an example, the frequency ratio (FR), index of entropy (IOE), Relief-F algorithm, and weights-of-evidence (WOE) Bayesian model were used to sort and screen the importance of 20 LSM factors; then, the LSMs generated based on different factor sets modeled are evaluated and further scored. The results showed that the IOE screening factor was better than the FR, Relief-F, and WOE Bayesian models in the case of retaining no fewer than eight factors; the score for 20 factors without screening was 45 points, and the score for 12 factors screened based on the IOE was 44.8 points, indicating that there was an optimal retention number that had little effect on the LSM results when IOE screening was used. The core factor set obtained by the method for comparing the increase in scores and the increase in corresponding factors effectively improved the accuracy of the LSM results, thus verifying the effectiveness of the proposed method for ranking the importance of LSM factors. The method proposed in this study can effectively screen the key LSM factors and improve the accuracy and scientific soundness of LSM results. Full article

(This article belongs to the Special Issue Innovation and Sustainable Development of Remote Sensing Technology)

► Show Figures

Figure 1

17 pages, 8862 KiB

Open AccessArticle

Monitoring Marine Oil Spills in Hyperspectral and Multispectral Remote Sensing Data by the Spectral Gene Extraction (SGE) Method

by Dong Zhao, Bin Tan, Haitao Zhang and Rui Deng

Sustainability 2022, 14(20), 13696; https://doi.org/10.3390/su142013696 - 21 Oct 2022

Cited by 5 | Viewed by 2275

Abstract

Oil spill incidents threaten the marine ecological environment. Detecting sea surface oil slicks by remote sensing images provides support for the efficient treatment of oil spills. This is important for sustainable marine development. However, traditional methods based on field analysis are time-consuming. Spectral [...] Read more.

Oil spill incidents threaten the marine ecological environment. Detecting sea surface oil slicks by remote sensing images provides support for the efficient treatment of oil spills. This is important for sustainable marine development. However, traditional methods based on field analysis are time-consuming. Spectral indices lack applicability. In addition, traditional machine learning methods strictly rely on training and testing samples which are in short supply in oil spill images. Inspired by the spectral DNA encoding method, a spectral gene extraction (SGE) method was proposed to detect oil spills in hyperspectral images (HSI) and multispectral images (MSI). The SGE method contained a parameter and two strategies. The parameter of elimination was designed based on the population genetic frequency. It was used to control the number of spectral genes. The spectral gene extraction strategies, named largest in-class similarity (LIS) strategy and largest inter-class difference (LID) strategy, were proposed to mine the spectral genes by oil spill samples. The oil spills would be determined by calculating the similarity of the extracted spectral genes to the DNA encoded images. In this research, the SGE method was validated by two AVIRIS images of the Gulf of Mexico oil spill, one MODIS image of the Gulf of Mexico oil spill, and one Landsat 8 image of a Persian Gulf oil spill. The oil spills in different remote sensing images could be detected accurately by the proposed method in a small set of samples. Experimental results indicated that the proposed method was suitable for detecting marine oil spills in AVIRIS, MODIS, and Landsat 8 images. In addition, the SGE method with the LIS strategy was more suitable for detecting oil spills in HSI. Its proper elimination rates were 0.8~1.0. The SGE method with the LID strategy was more suitable for detecting oil spills in MSI. Its proper elimination rates were 0.5~0.7. Full article

(This article belongs to the Special Issue Innovation and Sustainable Development of Remote Sensing Technology)

► Show Figures

Figure 1

19 pages, 10276 KiB

Open AccessArticle

Prior Knowledge-Based Deep Convolutional Neural Networks for Fine Classification of Land Covers in Surface Mining Landscapes

by Mingjie Qian, Yifan Li, Yunbo Zhao and Xuting Yu

Sustainability 2022, 14(19), 12563; https://doi.org/10.3390/su141912563 - 02 Oct 2022

Cited by 1 | Viewed by 1247

Abstract

Land cover classification is critical for urban sustainability applications. Although deep convolutional neural networks (DCNNs) have been widely utilized, they have rarely been used for land cover classification of complex landscapes. This study proposed the prior knowledge-based pretrained DCNNs (i.e., VGG and Xception) [...] Read more.

Land cover classification is critical for urban sustainability applications. Although deep convolutional neural networks (DCNNs) have been widely utilized, they have rarely been used for land cover classification of complex landscapes. This study proposed the prior knowledge-based pretrained DCNNs (i.e., VGG and Xception) for fine land cover classifications of complex surface mining landscapes. ZiYuan-3 data collected over an area of Wuhan City, China, in 2012 and 2020 were used. The ZiYuan-3 imagery consisted of multispectral imagery with four bands and digital terrain model data. Based on prior knowledge, the inputs of true and false color images were initially used. Then, a combination of the first and second principal components of the four bands and the digital terrain model data (PD) was examined. In addition, the combination of red and near-infrared bands and digital terrain model data (43D) was evaluated (i.e., VGG-43D and Xcep-43D). The results indicate that: (1) the input of 43D performed better than the others; (2) VGG-43D achieved the best overall accuracy values; (3) although the use of PD did not produce the best models, it also provides a strategy for integrating DCNNs and multi-band and multimodal data. These findings are valuable for future applications of DCNNs to determine fine land cover classifications in complex landscapes. Full article

(This article belongs to the Special Issue Innovation and Sustainable Development of Remote Sensing Technology)

► Show Figures

Figure 1

21 pages, 6355 KiB

Open AccessArticle

Three-Stream and Double Attention-Based DenseNet-BiLSTM for Fine Land Cover Classification of Complex Mining Landscapes

by Diya Zhang, Jiake Leng, Xianju Li, Wenxi He and Weitao Chen

Sustainability 2022, 14(19), 12465; https://doi.org/10.3390/su141912465 - 30 Sep 2022

Cited by 4 | Viewed by 1463

Abstract

The fine classification of land cover around complex mining areas is important for environmental protection and sustainable development. Although some advances have been made in the utilization of high-resolution remote sensing imagery and classification algorithms, the following issues still remain: (1) how the [...] Read more.

The fine classification of land cover around complex mining areas is important for environmental protection and sustainable development. Although some advances have been made in the utilization of high-resolution remote sensing imagery and classification algorithms, the following issues still remain: (1) how the multimodal spectral–spatial and topographic features can be learned for complex mining areas; (2) how the key features can be extracted; and (3) how the contextual information can be captured among different features. In this study, we proposed a novel model comprising the following three main strategies: (1) design comprising a three-stream multimodal feature learning and post-fusion method; (2) integration of deep separable asymmetric convolution blocks and parallel channel and spatial attention mechanisms into the DenseNet architecture; and (3) use of a bidirectional long short-term memory (BiLSTM) network to further learn cross-channel context features. The experiments were carried out in Wuhan City, China using ZiYuan-3 imagery. The proposed model was found to exhibit a better performance than other models, with an overall accuracy of 98.65% ± 0.05% and an improvement of 4.03% over the basic model. In addition, the proposed model yielded an obviously better visual prediction map for the entire study area. Overall, the proposed model is beneficial for multimodal feature learning and complex landscape applications. Full article

(This article belongs to the Special Issue Innovation and Sustainable Development of Remote Sensing Technology)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Innovation and Sustainable Development of Remote Sensing Technology

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI