remotesensing-logo

Journal Browser

Journal Browser

Machine Learning Methods for Environmental Monitoring

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 October 2021) | Viewed by 67280

Special Issue Editor


E-Mail Website
Guest Editor
Institute of Landscape Ecology, University of Münster, 48149 Münster, Germany
Interests: remote sensing; machine learning; environmental monitoring

Special Issue Information

Dear Colleagues,

Today, environmental monitoring is becoming an increasingly important issue when considering climate and land cover change and its consequences for the environment. Current earth observation satellites provide information with advanced spatial and temporal details that increases the potential of remote sensing to reveal spatial and temporal patterns and trends. In this context, machine learning algorithms have shown to be a powerful method to link remote sensing information to relevant environmental variables by accounting for the complexity and nonlinearity found in nature. The combination of remote sensing data and machine learning methods hence offers great but not yet fully exploited possibilities to monitor environmental variables across disciplines (e.g., biodiversity research, agriculture, forestry, and climatology) and on different temporal and spatial scales. However, recent studies also indicate ongoing challenges when machine learning methods are applied to remote sensing data. Spatial and temporal dependencies in the data, for example, challenge the application of machine learning algorithms and call for new modelling strategies that take the characteristics of remote sensing data into account.

This Special Issue aims to advance the application of machine learning algorithms for remote sensing-based environmental monitoring. We welcome methodological contributions in terms of novel machine learning strategies and innovative developments towards the reliability and robustness of the results. We further welcome applied contributions that demonstrate the potential and the challenges of machine learning applied to remote sensing in the context of environmental monitoring.

We are looking forward to an interesting collection of contributions!

Prof. Dr. Hanna Meyer
Guest Editor

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

  • Earth observation
  • Ecosystem dynamics
  • Environmental change
  • Machine learning strategies
  • Predictive modelling
  • Satellite imagery
  • Time series

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (8 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Other

24 pages, 3136 KiB  
Article
Potential of Airborne LiDAR Derived Vegetation Structure for the Prediction of Animal Species Richness at Mount Kilimanjaro
by Alice Ziegler, Hanna Meyer, Insa Otte, Marcell K. Peters, Tim Appelhans, Christina Behler, Katrin Böhning-Gaese, Alice Classen, Florian Detsch, Jürgen Deckert, Connal D. Eardley, Stefan W. Ferger, Markus Fischer, Friederike Gebert, Michael Haas, Maria Helbig-Bonitz, Andreas Hemp, Claudia Hemp, Victor Kakengi, Antonia V. Mayr, Christine Ngereza, Christoph Reudenbach, Juliane Röder, Gemma Rutten, David Schellenberger Costa, Matthias Schleuning, Axel Ssymank, Ingolf Steffan-Dewenter, Joseph Tardanico, Marco Tschapka, Maximilian G. R. Vollstädt, Stephan Wöllauer, Jie Zhang, Roland Brandl and Thomas Naussadd Show full author list remove Hide full author list
Remote Sens. 2022, 14(3), 786; https://doi.org/10.3390/rs14030786 - 8 Feb 2022
Cited by 2 | Viewed by 4365
Abstract
The monitoring of species and functional diversity is of increasing relevance for the development of strategies for the conservation and management of biodiversity. Therefore, reliable estimates of the performance of monitoring techniques across taxa become important. Using a unique dataset, this study investigates [...] Read more.
The monitoring of species and functional diversity is of increasing relevance for the development of strategies for the conservation and management of biodiversity. Therefore, reliable estimates of the performance of monitoring techniques across taxa become important. Using a unique dataset, this study investigates the potential of airborne LiDAR-derived variables characterizing vegetation structure as predictors for animal species richness at the southern slopes of Mount Kilimanjaro. To disentangle the structural LiDAR information from co-factors related to elevational vegetation zones, LiDAR-based models were compared to the predictive power of elevation models. 17 taxa and 4 feeding guilds were modeled and the standardized study design allowed for a comparison across the assemblages. Results show that most taxa (14) and feeding guilds (3) can be predicted best by elevation with normalized RMSE values but only for three of those taxa and two of those feeding guilds the difference to other models is significant. Generally, modeling performances between different models vary only slightly for each assemblage. For the remaining, structural information at most showed little additional contribution to the performance. In summary, LiDAR observations can be used for animal species prediction. However, the effort and cost of aerial surveys are not always in proportion with the prediction quality, especially when the species distribution follows zonal patterns, and elevation information yields similar results. Full article
(This article belongs to the Special Issue Machine Learning Methods for Environmental Monitoring)
Show Figures

Figure 1

30 pages, 2190 KiB  
Article
Monitoring Forest Health Using Hyperspectral Imagery: Does Feature Selection Improve the Performance of Machine-Learning Techniques?
by Patrick Schratz, Jannes Muenchow, Eugenia Iturritxa, José Cortés, Bernd Bischl and Alexander Brenning
Remote Sens. 2021, 13(23), 4832; https://doi.org/10.3390/rs13234832 - 28 Nov 2021
Cited by 9 | Viewed by 4109
Abstract
This study analyzed highly correlated, feature-rich datasets from hyperspectral remote sensing data using multiple statistical and machine-learning methods. The effect of filter-based feature selection methods on predictive performance was compared. In addition, the effect of multiple expert-based and data-driven feature sets, derived from [...] Read more.
This study analyzed highly correlated, feature-rich datasets from hyperspectral remote sensing data using multiple statistical and machine-learning methods. The effect of filter-based feature selection methods on predictive performance was compared. In addition, the effect of multiple expert-based and data-driven feature sets, derived from the reflectance data, was investigated. Defoliation of trees (%), derived from in situ measurements from fall 2016, was modeled as a function of reflectance. Variable importance was assessed using permutation-based feature importance. Overall, the support vector machine (SVM) outperformed other algorithms, such as random forest (RF), extreme gradient boosting (XGBoost), and lasso (L1) and ridge (L2) regressions by at least three percentage points. The combination of certain feature sets showed small increases in predictive performance, while no substantial differences between individual feature sets were observed. For some combinations of learners and feature sets, filter methods achieved better predictive performances than using no feature selection. Ensemble filters did not have a substantial impact on performance. The most important features were located around the red edge. Additional features in the near-infrared region (800–1000 nm) were also essential to achieve the overall best performances. Filter methods have the potential to be helpful in high-dimensional situations and are able to improve the interpretation of feature effects in fitted models, which is an essential constraint in environmental modeling studies. Nevertheless, more training data and replication in similar benchmarking studies are needed to be able to generalize the results. Full article
(This article belongs to the Special Issue Machine Learning Methods for Environmental Monitoring)
Show Figures

Graphical abstract

21 pages, 14903 KiB  
Article
Learning to Identify Illegal Landfills through Scene Classification in Aerial Images
by Rocio Nahime Torres and Piero Fraternali
Remote Sens. 2021, 13(22), 4520; https://doi.org/10.3390/rs13224520 - 10 Nov 2021
Cited by 41 | Viewed by 5368
Abstract
Illegal landfills are uncontrolled disposals of waste that cause severe environmental and health risk. Discovering them as early as possible is of prominent importance for preventing hazards, such as fire pollution and leakage. Before the digital era, the only means to detect illegal [...] Read more.
Illegal landfills are uncontrolled disposals of waste that cause severe environmental and health risk. Discovering them as early as possible is of prominent importance for preventing hazards, such as fire pollution and leakage. Before the digital era, the only means to detect illegal waste dumps was the on site inspection of potentially suspicious sites, a procedure extremely costly and impossible to scale to a vast territory. With the advent of Earth observation technology, scanning the territory via aerial images has become possible. However, manual image interpretation remains a complex and time-consuming task that requires expert skill. Photo interpretation can be partially automated by embedding the expert knowledge within a data driven classifier trained with samples provided by human annotators. In this paper, the detection of illegal landfills is formulated as a multi-scale scene classification problem. Scene elements positioning and spatial relations constitute hints of the presence of illegal waste dumps. A dataset of ≈3000 images (20 cm resolution per pixel) was created with the help of expert photo interpreters. A combination of ResNet50 and Feature Pyramid Network (FPN) elements accounting for different object scales achieves 88% precision with an 87% of recall in a test area. The results proved the feasibility of applying convolutional neural networks for scene classification in this scenario to optimize the process of waste dumps detection. Full article
(This article belongs to the Special Issue Machine Learning Methods for Environmental Monitoring)
Show Figures

Figure 1

25 pages, 91711 KiB  
Article
Coral Reef Mapping with Remote Sensing and Machine Learning: A Nurture and Nature Analysis in Marine Protected Areas
by Camila Brasil Louro da Silveira, Gil Marcelo Reuss Strenzel, Mauro Maida, Ana Lídia Bertoldi Gaspar and Beatrice Padovani Ferreira
Remote Sens. 2021, 13(15), 2907; https://doi.org/10.3390/rs13152907 - 24 Jul 2021
Cited by 29 | Viewed by 8860
Abstract
Mapping habitats is essential to assist strategic decisions regarding the use and protection of coral reefs. Coupled with machine learning (ML) algorithms, remote sensing has allowed detailed mapping of reefs at meaningful scales. Here we integrated WorldView-3 and Landsat-8 imagery and ML techniques [...] Read more.
Mapping habitats is essential to assist strategic decisions regarding the use and protection of coral reefs. Coupled with machine learning (ML) algorithms, remote sensing has allowed detailed mapping of reefs at meaningful scales. Here we integrated WorldView-3 and Landsat-8 imagery and ML techniques to produce a map of suitable habitats for the occurrence of a model species, the hydrocoral Millepora alcicornis, in coral reefs located inside marine protected areas in Northeast Brazil. Conservation and management efforts in the region were also analyzed, integrating human use layers to the ecological seascape. Three ML techniques were applied: two to derive base layers, namely geographically weighted regressions for bathymetry and support vector machine classifier (SVM) for habitat mapping, and one to build the species distribution model (MaxEnt) for Millepora alcicornis, a conspicuous and important reef-building species in the area. Additionally, human use was mapped based on the presence of tourists and fishers. SVM yielded 15 benthic classes (e.g., seagrass, sand, coral), with an overall accuracy of 79%. Bathymetry and its derivative layers depicted the topographical complexity of the area. The Millepora alcicornis distribution model identified distance from the shore and depth as topographical factors limiting the settling and growth of coral colonies. The most important variables were ecological, showing the importance of maintaining high biodiversity in the ecosystem. The comparison of the habitat suitability model with species absence and human use maps indicated the impact of direct human activities as potential inhibitors of coral development. Results reinforce the importance of the establishment of no-take zones and other protective measures for maintaining local biodiversity. Full article
(This article belongs to the Special Issue Machine Learning Methods for Environmental Monitoring)
Show Figures

Figure 1

18 pages, 7841 KiB  
Article
Large-Scale River Mapping Using Contrastive Learning and Multi-Source Satellite Imagery
by Zhihao Wei, Kebin Jia, Pengyu Liu, Xiaowei Jia, Yiqun Xie and Zhe Jiang
Remote Sens. 2021, 13(15), 2893; https://doi.org/10.3390/rs13152893 - 23 Jul 2021
Cited by 15 | Viewed by 4214
Abstract
River system is critical for the future sustainability of our planet but is always under the pressure of food, water and energy demands. Recent advances in machine learning bring a great potential for automatic river mapping using satellite imagery. Surface river mapping can [...] Read more.
River system is critical for the future sustainability of our planet but is always under the pressure of food, water and energy demands. Recent advances in machine learning bring a great potential for automatic river mapping using satellite imagery. Surface river mapping can provide accurate and timely water extent information that is highly valuable for solid policy and management decisions. However, accurate large-scale river mapping remains challenging given limited labels, spatial heterogeneity and noise in satellite imagery (e.g., clouds and aerosols). In this paper, we propose a new multi-source data-driven method for large-scale river mapping by combining multi-spectral imagery and synthetic aperture radar data. In particular, we build a multi-source data segmentation model, which uses contrastive learning to extract the common information between multiple data sources while also preserving distinct knowledge from each data source. Moreover, we create the first large-scale multi-source river imagery dataset based on Sentinel-1 and Sentinel-2 satellite data, along with 1013 handmade accurate river segmentation mask (which will be released to the public). In this dataset, our method has been shown to produce superior performance (F1-score is 91.53%) over multiple state-of-the-art segmentation algorithms. We also demonstrate the effectiveness of the proposed contrastive learning model in mapping river extent when we have limited and noisy data. Full article
(This article belongs to the Special Issue Machine Learning Methods for Environmental Monitoring)
Show Figures

Graphical abstract

29 pages, 8523 KiB  
Article
Random Forest Spatial Interpolation
by Aleksandar Sekulić, Milan Kilibarda, Gerard B.M. Heuvelink, Mladen Nikolić and Branislav Bajat
Remote Sens. 2020, 12(10), 1687; https://doi.org/10.3390/rs12101687 - 25 May 2020
Cited by 179 | Viewed by 23076
Abstract
For many decades, kriging and deterministic interpolation techniques, such as inverse distance weighting and nearest neighbour interpolation, have been the most popular spatial interpolation techniques. Kriging with external drift and regression kriging have become basic techniques that benefit both from spatial autocorrelation and [...] Read more.
For many decades, kriging and deterministic interpolation techniques, such as inverse distance weighting and nearest neighbour interpolation, have been the most popular spatial interpolation techniques. Kriging with external drift and regression kriging have become basic techniques that benefit both from spatial autocorrelation and covariate information. More recently, machine learning techniques, such as random forest and gradient boosting, have become increasingly popular and are now often used for spatial interpolation. Some attempts have been made to explicitly take the spatial component into account in machine learning, but so far, none of these approaches have taken the natural route of incorporating the nearest observations and their distances to the prediction location as covariates. In this research, we explored the value of including observations at the nearest locations and their distances from the prediction location by introducing Random Forest Spatial Interpolation (RFSI). We compared RFSI with deterministic interpolation methods, ordinary kriging, regression kriging, Random Forest and Random Forest for spatial prediction (RFsp) in three case studies. The first case study made use of synthetic data, i.e., simulations from normally distributed stationary random fields with a known semivariogram, for which ordinary kriging is known to be optimal. The second and third case studies evaluated the performance of the various interpolation methods using daily precipitation data for the 2016–2018 period in Catalonia, Spain, and mean daily temperature for the year 2008 in Croatia. Results of the synthetic case study showed that RFSI outperformed most simple deterministic interpolation techniques and had similar performance as inverse distance weighting and RFsp. As expected, kriging was the most accurate technique in the synthetic case study. In the precipitation and temperature case studies, RFSI mostly outperformed regression kriging, inverse distance weighting, random forest, and RFsp. Moreover, RFSI was substantially faster than RFsp, particularly when the training dataset was large and high-resolution prediction maps were made. Full article
(This article belongs to the Special Issue Machine Learning Methods for Environmental Monitoring)
Show Figures

Graphical abstract

27 pages, 22737 KiB  
Article
Tree Crown Delineation Algorithm Based on a Convolutional Neural Network
by José R. G. Braga, Vinícius Peripato, Ricardo Dalagnol, Matheus P. Ferreira, Yuliya Tarabalka, Luiz E. O. C. Aragão, Haroldo F. de Campos Velho, Elcio H. Shiguemori and Fabien H. Wagner
Remote Sens. 2020, 12(8), 1288; https://doi.org/10.3390/rs12081288 - 18 Apr 2020
Cited by 92 | Viewed by 11581
Abstract
Tropical forests concentrate the largest diversity of species on the planet and play a key role in maintaining environmental processes. Due to the importance of those forests, there is growing interest in mapping their components and getting information at an individual tree level [...] Read more.
Tropical forests concentrate the largest diversity of species on the planet and play a key role in maintaining environmental processes. Due to the importance of those forests, there is growing interest in mapping their components and getting information at an individual tree level to conduct reliable satellite-based forest inventory for biomass and species distribution qualification. Individual tree crown information could be manually gathered from high resolution satellite images; however, to achieve this task at large-scale, an algorithm to identify and delineate each tree crown individually, with high accuracy, is a prerequisite. In this study, we propose the application of a convolutional neural network—Mask R-CNN algorithm—to perform the tree crown detection and delineation. The algorithm uses very high-resolution satellite images from tropical forests. The results obtained are promising—the R e c a l l , P r e c i s i o n , and F 1 score values obtained were were 0.81 , 0.91 , and 0.86 , respectively. In the study site, the total of tree crowns delineated was 59,062 . These results suggest that this algorithm can be used to assist the planning and conduction of forest inventories. As the algorithm is based on a Deep Learning approach, it can be systematically trained and used for other regions. Full article
(This article belongs to the Special Issue Machine Learning Methods for Environmental Monitoring)
Show Figures

Graphical abstract

Other

Jump to: Research

11 pages, 3370 KiB  
Technical Note
Semi-Automatic Generation of Training Samples for Detecting Renewable Energy Plants in High-Resolution Aerial Images
by Maximilian Kleebauer, Daniel Horst and Christoph Reudenbach
Remote Sens. 2021, 13(23), 4793; https://doi.org/10.3390/rs13234793 - 26 Nov 2021
Cited by 7 | Viewed by 2042
Abstract
Deep learning (DL)—in particular convolutional neural networks (CNN)—methods are widely spread in object detection and recognition of remote sensing images. In the domain of DL, there is a need for large numbers of training samples. These samples are mostly generated based on manual [...] Read more.
Deep learning (DL)—in particular convolutional neural networks (CNN)—methods are widely spread in object detection and recognition of remote sensing images. In the domain of DL, there is a need for large numbers of training samples. These samples are mostly generated based on manual identification. Identifying and labelling these objects is very time-consuming. The developed approach proposes a partially automated procedure for the sample creation and avoids manual labelling of rooftop photovoltaic (PV) systems. By combining address data of existing rooftop PV systems from the German Plant Register, the Georeferenced Address Data and the Official House Surroundings Germany, a partially automated generation of training samples is achieved. Using a selection of 100,000 automatically generated samples, a network using a RetinaNet-based architecture combining ResNet101, a feature pyramid network, a classification and a regression network is trained, applied on a large area and post-filtered by intersection with additional automatically identified locations of existing rooftop PV systems. Based on a proof-of-concept application, a second network is trained with the filtered selection of approximately 51,000 training samples. In two independent test applications using high-resolution aerial images of Saarland in Germany, buildings with PV systems are detected with a precision of at least 92.77 and a recall of 84.47. Full article
(This article belongs to the Special Issue Machine Learning Methods for Environmental Monitoring)
Show Figures

Figure 1

Back to TopTop