Submit to Remote Sensing Review for Remote Sensing Propose a Special Issue

Journal Browser

Machine Learning for Spatiotemporal Remote Sensing Data

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Related Special Issue
Published Papers

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Environmental Remote Sensing".

Deadline for manuscript submissions: closed (31 December 2023) | Viewed by 18255

Share This Special Issue

Special Issue Editors

Prof. Dr. Lianfa Li

E-Mail Website
Guest Editor

State Key Laboratory of Resources and Environmental Information Systems, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Datun Road, Beijing 100101, China
Interests: spatial statistics; machine learning; spatiotemporal data mining; remote sensing
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Xiaomei Yang

E-Mail Website
Guest Editor

State Key Laboratory of Resources and Environmental Information Systems, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Datun Road, Beijing 100101, China
Interests: coastal remote sensing and GIS; monitoring and assessment; coastal hazards and resilience
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Yong Ge

E-Mail Website
Guest Editor

State Key Laboratory of Resources and Environmental Information Systems, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Datun Road, Beijing 100101, China
Interests: information extraction; uncertainty assessment; image processing and analysis; spatial statistics; classification
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Monitoring spatiotemporal changes in geospatial features such as land cover, land use, and meteorology is critical for practical applications of remotely sensed data. However, spatiotemporal modeling of remote sensing data is challenging due to massive missing values caused by clouds or other geospatial features that are characterized by high reflectivity, inconsistency and heterogeneity of spatiotemporal dependencies. Although traditional machine learning methods can include temporal variables in the model to account for temporal variance, due to their lack or limitation of explicit spatiotemporal dependencies, confounding bias may be introduced by mixing spatial and temporal covariates, especially for classification by remote sensing data. Modern deep learning offers us new opportunities, including flexible network structures, such as 3D CNN, CNN-LSTM, CovLSTM, and CNN-Transformer, for explicit spatiotemporal interdependent modeling and efficient parallel computing for processing massive spatiotemporal data input. Whereas deep learning has been widely applied in spatiotemporal predictions in computer vision, natural language processing, meteorology etc., due to the particularity and complexity of geospatial features, there are many issues to be explored in their use in spatiotemporal prediction of remote sensing data.

This Special Issue aims to cover machine learning methods and applications in various fields for spatiotemporal regression and classification of remote sensing data. Topics may cover anything from data structure and processing, spatiotemporal fusion, spatiotemporal interdependent modeling, to mechanisms and prediction interpretation. In particular, deep learning methods and their comparisons with other machine learning methods for spatiotemporal modeling are welcome. Articles may address, but are not limited to, the following topics:

Spatiotemporal modeling by remote sensing;
Monitoring of land-use or land-cover by remote sensing;
Spatiotemporal inversion of geospatial parameters;
Spatiotemporal deep learning in remote sensing;
Predictions by remote sensing;
Weather forecasting by remote sensing.

Prof. Dr. Lianfa Li
Prof. Dr. Xiaomei Yang
Prof. Dr. Yong Ge
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

spatiotemporal modeling
spatiotemporal dependency
spatiotemporal prediction
spatiotemporal fusion
forecast
machine learning
deep learning
regression
classification
remote sensing

Related Special Issue

Machine Learning for Spatiotemporal Remote Sensing Data (2nd Edition) in Remote Sensing

Published Papers (13 papers)

Download All Papers

Research

Jump to: Other

31 pages, 7316 KiB

Open AccessArticle

Spatio-Temporal Deep Learning-Based Forecasting of Surface Solar Irradiance: Leveraging Satellite Data and Feature Selection

by Jinyong Kim, Eunkyeong Kim, Seunghwan Jung, Minseok Kim, Baekcheon Kim and Sungshin Kim

Remote Sens. 2024, 16(5), 888; https://doi.org/10.3390/rs16050888 - 02 Mar 2024

Viewed by 688

Abstract

This paper proposes a method for forecasting surface solar irradiance (SSI), the most critical factor in solar photovoltaic (PV) power generation. The proposed method uses 16-channel data obtained by the GEO-KOMPSAT-2A (GK2A) satellite of South Korea as the main data for SSI forecasting. To determine feature variables related to SSI from the 16-channel data, the differences and ratios between the channels were utilized. Additionally, to consider the fundamental characteristics of SSI originating from the sun, solar geometry parameters, such as solar declination (SD), solar elevation angle (SEA), and extraterrestrial solar radiation (ESR), were used. Deep learning-based feature selection (Deep-FS) was employed to select appropriate feature variables that affect SSI from various feature variables extracted from the 16-channel data. Lastly, spatio-temporal deep learning models, such as convolutional neural network–long short-term memory (CNN-LSTM) and CNN–gated recurrent unit (CNN-GRU), which can simultaneously reflect temporal and spatial characteristics, were used to forecast SSI. Experiments conducted to verify the proposed method against conventional methods confirmed that the proposed method delivers superior SSI forecasting performance. Full article

(This article belongs to the Special Issue Machine Learning for Spatiotemporal Remote Sensing Data)

► Show Figures

Figure 1

22 pages, 7645 KiB

Open AccessArticle

A Reconstructing Model Based on Time–Space–Depth Partitioning for Global Ocean Dissolved Oxygen Concentration

by Zhenguo Wang, Cunjin Xue and Bo Ping

Remote Sens. 2024, 16(2), 228; https://doi.org/10.3390/rs16020228 - 06 Jan 2024

Viewed by 779

Abstract

Dissolved oxygen (DO) is essential for assessing and monitoring the health of marine ecosystems. The phenomenon of ocean deoxygenation is widely recognized. Nevertheless, the limited availability of observations poses a challenge in achieving a comprehensive understanding of global ocean DO dynamics and trends. The study addresses the challenge of unevenly distributed Argo DO data by developing time–space–depth machine learning (TSD-ML), a novel machine learning-based model designed to enhance reconstruction accuracy in data-sparse regions. TSD-ML partitions Argo data into segments based on time, depth, and spatial dimensions, and conducts model training for each segment. This research contrasts the effectiveness of partitioned and non-partitioned modeling approaches using three distinct ML regression methods. The results reveal that TSD-ML significantly enhances reconstruction accuracy in areas with uneven DO data distribution, achieving a 30% reduction in root mean square error (RMSE) and a 20% decrease in mean absolute error (MAE). In addition, a comparison with WOA18 and GLODAPv2 ship survey data confirms the high accuracy of the reconstructions. Analysis of the reconstructed global ocean DO trends over the past two decades indicates an alarming expansion of anoxic zones. Full article

(This article belongs to the Special Issue Machine Learning for Spatiotemporal Remote Sensing Data)

► Show Figures

Figure 1

25 pages, 4194 KiB

Open AccessArticle

Learning Global Evapotranspiration Dataset Corrections from a Water Cycle Closure Supervision

by Tristan Hascoet, Victor Pellet, Filipe Aires and Tetsuya Takiguchi

Remote Sens. 2024, 16(1), 170; https://doi.org/10.3390/rs16010170 - 31 Dec 2023

Viewed by 747

Abstract

Evapotranspiration (E) is one of the most uncertain components of the global water cycle (WC). Improving global E estimates is necessary to improve our understanding of climate and its impact on available surface water resources. This work presents a methodology for [...] Read more.

^{\circ}

resolution. A principled approach is proposed to firstly use indirect information from the other water components to correct E estimates at the catchment level, and secondly to extend this sparse catchment-level information to global pixel-level corrections using machine learning (ML). Several E satellite products are available, each with its own errors (both random and systematic). Four such global E datasets are used to validate the proposed approach and highlight its ability to extract seasonal and regional systematic biases. The resulting E corrections are shown to accurately generalize WC closure constraints to unseen catchments. With an average deviation of 14% from the original E datasets, the proposed method achieves up to 20% WC residual reduction on the most favorable dataset. Full article

(This article belongs to the Special Issue Machine Learning for Spatiotemporal Remote Sensing Data)

► Show Figures

Figure 1

24 pages, 27430 KiB

Open AccessArticle

Spatial Distribution of Multiple Atmospheric Pollutants in China from 2015 to 2020

by Yufeng Chi, Yu Zhan, Kai Wang and Hong Ye

Remote Sens. 2023, 15(24), 5705; https://doi.org/10.3390/rs15245705 - 12 Dec 2023

Viewed by 868

Abstract

The pursuit of higher-resolution and more reliable spatial distribution simulation results for air pollutants is important to human health and environmental safety. However, the lack of high-resolution remote sensing retrieval parameters for gaseous pollutants (sulfur dioxide and ozone) limits the simulation effect to a 1 km resolution. To address this issue, we sequentially generated and optimized the spatial distributions of near-surface PM_2.5, SO₂, and ozone at a 1 km resolution in China through two approaches. First, we employed spatial sampling, random ID, and parameter convolution methods to jointly optimize a tree-based machine-learning gradient-boosting framework, LightGBM, and improve the performance of spatial air pollutant simulations. Second, we simulated PM_2.5, used the simulated PM_2.5 result to simulate SO₂, and then used the simulated SO₂ to simulate ozone. We improved the stability of 1 km-resolution SO₂ and ozone products through the proposed sequence of multiple-pollutant simulations. The cross-validation (CV) of the random sample yielded an R² of 0.90 and an RMSE of 9.62 µg∙m⁻³ for PM_2.5, an R² of 0.92 and an RMSE of 3.9 µg∙m⁻³ for SO₂, and an R² of 0.94 and an RMSE of 5.9 µg∙m⁻³ for ozone, which are values better than those in previous related studies. In addition, we tested the reliability of PM_2.5, SO₂, and ozone products in China through spatial distribution reliability analysis and parameter importance reliability analysis. The PM_2.5, SO₂, and ozone simulation models and multiple-air-pollutant (MuAP) products generated by the two optimization methods proposed in this study are of great value for long-term, large-scale, and regional-scale air pollution monitoring and predictions, as well as population health assessments. Full article

(This article belongs to the Special Issue Machine Learning for Spatiotemporal Remote Sensing Data)

► Show Figures

Figure 1

21 pages, 63628 KiB

Open AccessArticle

Spatiotemporal Fusion Model of Remote Sensing Images Combining Single-Band and Multi-Band Prediction

by Zhiyuan Wang, Shuai Fang and Jing Zhang

Remote Sens. 2023, 15(20), 4936; https://doi.org/10.3390/rs15204936 - 12 Oct 2023

Cited by 1 | Viewed by 1173

Abstract

In recent years, convolutional neural network (CNN)-based spatiotemporal fusion (STF) models for remote sensing images have made significant progress. However, existing STF models may suffer from two main drawbacks. Firstly, multi-band prediction often generates a hybrid feature representation that includes information from all bands. This blending of features can lead to the loss or blurring of high-frequency details, making it challenging to reconstruct multi-spectral remote sensing images with significant spectral differences between bands. Another challenge in many STF models is the limited preservation of spectral information during 2D convolution operations. Combining all input channels’ convolution results into a single-channel output feature map can lead to the degradation of spectral dimension information. To address these issues and to strike a balance between avoiding hybrid features and fully utilizing spectral information, we propose a remote sensing image STF model that combines single-band and multi-band prediction (SMSTFM). The SMSTFM initially performs single-band prediction, generating separate predicted images for each band, which are then stacked together to form a preliminary fused image. Subsequently, the multi-band prediction module leverages the spectral dimension information of the input images to further enhance the preliminary predictions. We employ the modern ConvNeXt convolutional module as the primary feature extraction component. During the multi-band prediction phase, we enhance the spatial and channel information captures by replacing the 2D convolutions within ConvNeXt with 3D convolutions. In the experimental section, we evaluate our proposed algorithm on two public datasets with 16x resolution differences and one dataset with a 3x resolution difference. The results demonstrate that our SMSTFM achieves state-of-the-art performance on these datasets and is proven effective and reasonable through ablation studies. Full article

(This article belongs to the Special Issue Machine Learning for Spatiotemporal Remote Sensing Data)

► Show Figures

Graphical abstract

26 pages, 2247 KiB

Open AccessArticle

Forecasting PM₁₀ Levels Using Machine Learning Models in the Arctic: A Comparative Study

by Paolo Fazzini, Marco Montuori, Antonello Pasini, Alice Cuzzucoli, Ilaria Crotti, Emilio Fortunato Campana, Francesco Petracchini and Srdjan Dobricic

Remote Sens. 2023, 15(13), 3348; https://doi.org/10.3390/rs15133348 - 30 Jun 2023

Cited by 1 | Viewed by 967

Abstract

In this study, we present a statistical forecasting framework and assess its efficacy using a range of established machine learning algorithms for predicting Particulate Matter (PM) concentrations in the Arctic, specifically in Pallas (FI), Reykjavik (IS), and Tromso (NO). Our framework leverages historical ground measurements and 24 h predictions from nine models by the Copernicus Atmosphere Monitoring Service (CAMS) to provide PM₁₀ predictions for the following 24 h. Furthermore, we compare the performance of various memory cells based on artificial neural networks (ANN), including recurrent neural networks (RNNs), gated recurrent units (GRUs), long short-term memory networks (LSTMs), echo state networks (ESNs), and windowed multilayer perceptrons (MLPs). Regardless of the type of memory cell chosen, our results consistently show that the proposed framework outperforms the CAMS models in terms of mean squared error (MSE), with average improvements ranging from 25% to 40%. Furthermore, we examine the impact of outliers on the overall performance of the model. Full article

(This article belongs to the Special Issue Machine Learning for Spatiotemporal Remote Sensing Data)

► Show Figures

Graphical abstract

20 pages, 4349 KiB

Open AccessArticle

Spatiotemporal Evolution of Production–Living–Ecological Land and Its Eco-Environmental Response in China’s Coastal Zone

by Fengshuo Yang, Xiaomei Yang, Zhihua Wang, Yingjun Sun, Yinghui Zhang, Huaqiao Xing and Qi Wang

Remote Sens. 2023, 15(12), 3039; https://doi.org/10.3390/rs15123039 - 10 Jun 2023

Cited by 4 | Viewed by 1064

Abstract

High-intensity human activities have caused dramatic transformations of land function in China’s coastal zone, putting enormous pressure on the region’s ecological environment. It is urgent to fully understand the spatiotemporal evolution of the land-use function in the coastal zone to promote sustainable development. Therefore, based on CNLUCC data for 2000, 2010, and 2020, this study quantitatively explored the spatiotemporal evolution of production–living–ecological land (PLEL) and its eco-environmental response in China’s coastal zone by using multiple land-use analysis methods, gradient analysis, and the eco-environmental quality index. The results showed that over the past 20 years, the production land (PL) continued to decrease, whereas the living land (LL) and blue ecological land (BEL) increased. In the vertical direction, PL and the ecological land (EL) dominated in the northern and the southern coastal zone, respectively. In the horizontal direction, with increasing distance from the coastline, the green ecological land (GEL) increased, whereas it was the opposite for BEL. The transformations of PLEL were high and low frequency in the north and south, respectively. From 2000 to 2020, the eco-environmental quality of China’s coastal zone slightly degraded, with conditions that were “excellent in the south and poor in the north”. The eco-environmental qualities of each sub-coastal zone gradually improved with increasing distance from the coastline. The main transformation types that led to eco-environmental improvement and degradation were from other production lands (OPL) to blue ecological land (BEL) and BEL to OPL, respectively. The findings will guide PLEL planning, eco-environmental protection, and science-based land usage. Full article

(This article belongs to the Special Issue Machine Learning for Spatiotemporal Remote Sensing Data)

► Show Figures

Figure 1

29 pages, 18387 KiB

Open AccessArticle

Improved Spatiotemporal Information Fusion Approach Based on Bayesian Decision Theory for Land Cover Classification

by Yan Jin, Xudong Guan, Yong Ge, Yan Jia and Wenmei Li

Remote Sens. 2022, 14(23), 6003; https://doi.org/10.3390/rs14236003 - 26 Nov 2022

Cited by 4 | Viewed by 1339

Abstract

High-spatial-resolution (HSR) images and high-temporal-resolution (HTR) images have their unique advantages and can be replenished by each other effectively. For land cover classification, a series of spatiotemporal fusion algorithms were developed to acquire a high-resolution land cover map. The fusion processes focused on the single level, especially the pixel level, could ignore the different phenology changes and land cover changes. Based on Bayesian decision theory, this paper proposes a novel decision-level fusion for multisensor data to classify the land cover. The proposed Bayesian fusion (PBF) combines the classification accuracy of results and the class allocation uncertainty of classifiers in the estimation of conditional probability, which consider the detailed spectral information as well as the various phenology information. To deal with the scale inconsistency problem at the decision level, an object layer and an area factor are employed for unifying the spatial resolution of distinct images, which would be applied for evaluating the classification uncertainty related to the conditional probability inference. The approach was verified on two cases to obtain the HSR land cover maps, in comparison with the implementation of two single-source classification methods and the benchmark fusion methods. Analyses and comparisons of the different classification results showed that PBF outperformed the best performance. The overall accuracy of PBF for two cases rose by an average of 27.8% compared with two single-source classifications, and an average of 13.6% compared with two fusion classifications. This analysis indicated the validity of the proposed method for a large area of complex surfaces, demonstrating the high potential for land cover classification. Full article

(This article belongs to the Special Issue Machine Learning for Spatiotemporal Remote Sensing Data)

► Show Figures

Figure 1

18 pages, 6018 KiB

Open AccessArticle

Integrating Multi-Scale Remote-Sensing Data to Monitor Severe Forest Infestation in Response to Pine Wilt Disease

by Xiujuan Li, Yongxin Liu, Pingping Huang, Tong Tong, Linyuan Li, Yuejuan Chen, Ting Hou, Yun Su, Xiaoqi Lv, Wenxue Fu and Xiaojun Huang

Remote Sens. 2022, 14(20), 5164; https://doi.org/10.3390/rs14205164 - 15 Oct 2022

Cited by 7 | Viewed by 1917

Abstract

Pine wilt disease (PWD) is one of the most destructive forest diseases that has led to rapid wilting and mortality in susceptible host pine trees. Spatially explicit detection of pine wood nematode (PWN)-induced infestation is important for forest management, policy making, and practices. Previous studies have mapped forest disturbances in response to various forest diseases and/or insects over large areas using remote-sensing techniques, but these efforts were often constrained by the limited availability of ground truth information needed for the calibration and validation of moderate-resolution satellite algorithms in the process of linking plot-scale measurements to satellite data. In this study, we proposed a two-level up-sampling strategy by integrating unmanned aerial vehicle (UAV) surveys and high-resolution Radarsat-2 satellite imagery for expanding the number of training samples at the 30-m resampled Sentinel-1 resolution. Random forest algorithms were separately used in the prediction of the Radarsat-2 and Sentinel-1 infestation map induced by PWN. After data acquisition in Muping District during August and September 2021, we first verified the ability of a deep-learning-based object detection algorithm (i.e., YOLOv5 model) in the detection of infested trees from coregistered UAV-based RGB images (Average Precision (AP) of larger than 70% and R² of 0.94). A random forest algorithm trained using the up-sampling UAV infestation map reference and corresponding Radarsat-2 pixel values was then used to produce the Radarsat-2 infestation map, resulting in an overall accuracy of 72.57%. Another random forest algorithm trained using the Radarsat-2 infestation pixels with moderate and high severity (i.e., an infestation severity of larger than 0.25, where the value was empirically set based on a trade-off between classification accuracy and infection detectability) and corresponding Sentinel-1 pixel values was subsequently used to predict the Sentinel-1 infestation map, resulting in an overall accuracy of 87.63%, where the validation data are Radarsat-2 references rather than UAV references. The Sentinel-1 map was also validated by independent UAV surveys, with an overall accuracy of 76.30% and a Kappa coefficient of 0.45. We found that the expanded training samples by the integration of UAV and Radarsat-2 strengthened the medium-resolution Sentinel-1-based prediction model of PWD. This study demonstrates that the proposed method enables effective PWN infestation mapping over multiple scales. Full article

(This article belongs to the Special Issue Machine Learning for Spatiotemporal Remote Sensing Data)

► Show Figures

Graphical abstract

21 pages, 7859 KiB

Open AccessArticle

Spatiotemporally Continuous Reconstruction of Retrieved PM_2.5 Data Using an Autogeoi-Stacking Model in the Beijing-Tianjin-Hebei Region, China

by Wenhao Chu, Chunxiao Zhang, Yuwei Zhao, Rongrong Li and Pengda Wu

Remote Sens. 2022, 14(18), 4432; https://doi.org/10.3390/rs14184432 - 06 Sep 2022

Cited by 4 | Viewed by 1611

Abstract

Aerosol optical depth (AOD) observations have been widely used to generate wide-coverage PM_2.5 retrievals due to the adverse effects of long-term exposure to PM_2.5 and the sparsity and unevenness of monitoring sites. However, due to non-random missing and nighttime gaps in AOD products, obtaining spatiotemporally continuous hourly data with high accuracy has been a great challenge. Therefore, this study developed an automatic geo-intelligent stacking (autogeoi-stacking) model, which contained seven sub-models of machine learning and was stacked through a Catboost model. The autogeoi-stacking model used the automated feature engineering (autofeat) method to identify spatiotemporal characteristics of multi-source datasets and generate extra features through automatic non-linear changes of multiple original features. The 10-fold cross-validation (CV) evaluation was employed to evaluate the 24-hour and continuous ground-level PM_2.5 estimations in the Beijing-Tianjin-Hebei (BTH) region during 2018. The results showed that the autogeoi-stacking model performed well in the study area with the coefficient of determination (R²) of 0.88, the root mean squared error (RMSE) of 17.38 µg/m³, and the mean absolute error (MAE) of 10.71 µg/m³. The estimated PM_2.5 concentrations had an excellent performance during the day (8:00–18:00, local time) and night (19:00–07:00) (the cross-validation coefficient of determination (CV-R²): 0.90, 0.88), and captured hourly PM_2.5 variations well, even in the severe ambient air pollution event. On the seasonal scale, the R² values from high to low were winter, autumn, spring, and summer, respectively. Compared with the original stacking model, the improvement of R² with the autofeat and hyperparameter optimization approaches was up to 5.33%. In addition, the annual mean values indicated that the southern areas, such as Shijiazhuang, Xingtai, and Handan, suffered higher PM_2.5 concentrations. The northern regions (e.g., Zhangjiakou and Chengde) experienced low PM_2.5. In summary, the proposed method in this paper performed well and could provide ideas for constructing geoi-features and spatiotemporally continuous inversion products of PM_2.5. Full article

(This article belongs to the Special Issue Machine Learning for Spatiotemporal Remote Sensing Data)

► Show Figures

Graphical abstract

22 pages, 8054 KiB

Open AccessArticle

Long-Term and Bimonthly Estimation of Lake Water Extent Using Google Earth Engine and Landsat Data

by Tao Zhang, Hongxing Wang, Shanshan Hu, Shucheng You and Xiaomei Yang

Remote Sens. 2022, 14(12), 2893; https://doi.org/10.3390/rs14122893 - 17 Jun 2022

Cited by 1 | Viewed by 2259

Abstract

Lakes are one of the most important parts of the terrestrial hydrosphere. The long-term series of lake area dynamic data with high spatial-temporal resolution is of great significance to the study of global change of the water environment. Satellite observations (such as Landsat) have provided images since the 1970s, but there were challenges for the construction of long-term sequences of lake area on a monthly temporal scale. We proposed a temporal-spatial interpolation and rule-based (TSIRB) approach on the Google Earth Engine, which aims to achieve automatic water extraction and bimonthly sequence construction of lake area. There are three main steps of this method which include bimonthly image sequence construction, automatic water extraction, and anomaly rectification. We applied the TSIRB method to five typical lakes (covering salt lakes, river lagoons, and plateau alpine lakes), and constructed the bimonthly surface water dataset (BSWD) from 1987 to 2020. The accuracy assessment that was based on a confusion matrix and random sampling showed that the average overall accuracy (OA) of water extraction was 96.6%, and the average Kappa was 0.90. The BSWD sequence was compared with the lake water level observation data, and the results show that the BSWD data is closely correlated with the water level observation sequence, with correlation coefficient greater than 0.87. The BSWD improves the hollows in the global surface water (GSW) monthly data and has advantages in the temporal continuity of surface water data. The BSWD can provide a 30-m-scale and bimonthly series of surface water for more than 30 years, which shows good value for the long-term dynamic monitoring of lakes, especially in areas that are lacking in situ surveying data. Full article

(This article belongs to the Special Issue Machine Learning for Spatiotemporal Remote Sensing Data)

► Show Figures

Graphical abstract

20 pages, 5723 KiB

Open AccessArticle

Estimation of Regional Ground-Level PM_2.5 Concentrations Directly from Satellite Top-of-Atmosphere Reflectance Using A Hybrid Learning Model

by Yu Feng, Shurui Fan, Kewen Xia and Li Wang

Remote Sens. 2022, 14(11), 2714; https://doi.org/10.3390/rs14112714 - 06 Jun 2022

Cited by 6 | Viewed by 1867

Abstract

The accurate prediction of PM_2.5 concentrations is important for environmental protection. The accuracy of the commonly used prediction methods is not high; so, this paper proposes a PM_2.5 concentration prediction method based on a hybrid learning model. The Top-of-Atmosphere Reflectance (TOAR), PM_2.5 data decomposed by wavelets, and meteorological data were used as input features to build an integrated prediction model using random forest and LightGBM, which was applied to PM_2.5 concentration prediction in the Beijing–Tianjin–Hebei region. The practical application showed that the proposed method using TOAR, incorporating wavelet decomposition with meteorological element data, had an improvement of 0.06 in the R² of the model accuracy and a reduction of 2.93 and 1.14 in the root mean square error (RMSE) and mean absolute error (MAE), respectively, over the model using Aerosol Optical Depth (AOD). Our model had a prediction accuracy of R² of 0.91, which was better than the other models. We used this model to estimate and analyze the variation in PM_2.5 concentrations in the Beijing–Tianjin–Hebei region, and the results were the same as the actual PM_2.5 concentration distribution trend. Obviously, the proposed model has a high prediction accuracy and can avoid the errors caused by the limitations of the AOD inversion method. Full article

(This article belongs to the Special Issue Machine Learning for Spatiotemporal Remote Sensing Data)

► Show Figures

Figure 1

Other

Jump to: Research

19 pages, 1270 KiB

Open AccessTechnical Note

A Novel Deep Learning Model for Mining Nonlinear Dynamics in Lake Surface Water Temperature Prediction

by Zihan Hao, Weide Li, Jinran Wu, Shaotong Zhang and Shujuan Hu

Remote Sens. 2023, 15(4), 900; https://doi.org/10.3390/rs15040900 - 06 Feb 2023

Cited by 7 | Viewed by 1402

Abstract

As one of the critical indicators of the lake ecosystem, the lake surface water temperature is an important indicator for measuring lake ecological environment. However, there is a complex nonlinear relationship between lake surface water temperature and climate variables, making it difficult to accurately predict. Fortunately, satellite remote sensing provides a wealth of data to support further improvements in prediction accuracy. In this paper, we construct a new deep learning model for mining the nonlinear dynamics from climate variables to obtain more accurate prediction of lake surface water temperature. The proposed model consists of the variable correlation information module and the temporal correlation information module. The variable correlation information module based on the Self-Attention mechanism extracts key variable features that affect lake surface water temperature. Then, the features are input into the temporal correlation information module based on the Gated Recurrent Unit (GRU) model to learn the temporal variation patterns. The proposed model, called Attention-GRU, is then applied to lake surface water temperature prediction in Qinghai Lake, the largest inland lake located in the Tibetan Plateau region in China. Compared with the seven baseline models, the Attention-GRU model achieved the most accurate prediction results; notably, it significantly outperformed the Air2water model which is the classic model for lake surface water temperature prediction based on the volume-integrated heat balance equation. Finally, we analyzed the factors influencing the surface water temperature of Qinghai Lake. There are different degrees of direct and indirect effects of climatic variables, among which air temperature is the dominant factor. Full article

(This article belongs to the Special Issue Machine Learning for Spatiotemporal Remote Sensing Data)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Machine Learning for Spatiotemporal Remote Sensing Data

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Related Special Issue

Published Papers (13 papers)

Research

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI