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

Journal Browser

Land Use Classification with GIS and Remote Sensing Data Based on AI Technology

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
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 August 2022) | Viewed by 26682

Share This Special Issue

Special Issue Editors

Dr. Do-Hyung Kim

E-Mail Website
Guest Editor

Office of Innovation, United Nations Children’s Fund, New York, NY, USA
Interests: remote sensing; land use; land cover change; object detection; geospatial analysis
Special Issues, Collections and Topics in MDPI journals

Dr. Anupam Anand

E-Mail Website
Guest Editor

Independent Evaluation Office, Global Environment Facility, Washington, DC, USA
Interests: earth obsevation; land cover and land-use change; lidar; monitoring and evaluation; sustainable development; science-policy interface
Special Issues, Collections and Topics in MDPI journals

Dr. Joseph Bullock

E-Mail Website
Guest Editor

United Nations Global Pulse, New York, NY 10017, USA
Interests: remote sensing; artificial intelligence; settlement mapping; rapid mapping; disaster response

Dr. Miguel Luengo-Oroz

E-Mail Website
Guest Editor

United Nations Global Pulse, New York, NY 10017, USA
Interests: remote sensing; sustainable development; humanitarian action; artificial intelligence; image processing; global health

Special Issue Information

Dear Colleagues,

Remote sensing has been a very useful source of data to understand the changes on the earth’s surface. Land Cover classification based on the spectral signatures captured in remote sensing observations has been widely used to understand anthropogenic changes and their impact on the environment. At macro scale, such information has been invaluable for monitoring progress towards sustainable development goals and for informing the policymaking processes.

However, the application of remote sensing to analyze the changes in Land Use that are linked with socio-economic characteristics rather than physical drivers has been comparatively less explored.

Information on Land Use and its change can be extremely useful for humanitarian strategies and operations at regional and local scales. For example, the information on Land Use at a local scale can be used to support areas without specific types of essential services, for example, education and health care, etc.

The applications of remote sensing to characterize Land Use has been limited partly due to the lack of the means to extract contextual information from remote sensing data and also due to the lack of the resources required for such complex analysis. We have seen recent progress and applications of deep learning to extract complex contextual information from remote sensing data to understand socio-economic characteristics such as poverty which demonstrates the feasibility of using AI and remote sensing to better characterize Land Use and its change. Recent developments in AI algorithms and resources such as very high-resolution imagery, cloud-based computing platforms also enabled the applications of AI-based algorithms on remote sensing data for Land Use classification.

Nonetheless, there are still many obstacles for the successful applications of AI for land use characterization including lack of proper, curated training samples, scalability of AI algorithms and, applicability of deep learning algorithms to the different types of remote sensing data, etc.

This special issue welcomes papers that explore the various topics on the applications of AI to characterize Land Use and its change.

Dr. Do-Hyung Kim
Dr. Anupam Anand
Dr. Joseph Bullock
Dr. Miguel Luengo-Oroz
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

Novel Deep learning-based approach for land use classification
AI-based Land Use Change prediction models and their applications
Fusing secondary sources (e.g. mobile data, SNS data) and remote sensing data together for Land Use classification using AI
Quantification of biases in AI algorithms for Land Use classification
Quantification of errors and uncertainties in AI for land use classification and their drivers and implications
Scale issues in Land Use classification using AI
Innovative application of AI-based satellite image classification in humanitarian, developmental, and environmental sectors
‘White boxing’ AI for land use classification
Temporal dynamics of land use classification and change detection
Challenges and limitations of operational implementations of AI for land use classification
Privacy and ethical aspects from AI research on remote sensing and land use

Published Papers (7 papers)

Download All Papers

Research

Jump to: Other

38 pages, 138821 KiB

Open AccessArticle

A Multi-Temporal Network for Improving Semantic Segmentation of Large-Scale Landsat Imagery

by Xuan Yang, Bing Zhang, Zhengchao Chen, Yongqing Bai and Pan Chen

Remote Sens. 2022, 14(19), 5062; https://0-doi-org.brum.beds.ac.uk/10.3390/rs14195062 - 10 Oct 2022

Cited by 1 | Viewed by 1925

Abstract

With the development of deep learning, semantic segmentation technology has gradually become the mainstream technical method in large-scale multi-temporal landcover classification. Large-scale and multi-temporal are the two significant characteristics of Landsat imagery. However, the mainstream single-temporal semantic segmentation network lacks the constraints and assistance of pre-temporal information, resulting in unstable results, poor generalization ability, and inconsistency with the actual situation in the multi-temporal classification results. In this paper, we propose a multi-temporal network that introduces pre-temporal information as prior constrained auxiliary knowledge. We propose an element-wise weighting block module to improve the fine-grainedness of feature optimization. We propose a chained deduced classification strategy to improve multi-temporal classification’s stability and generalization ability. We label the large-scale multi-temporal Landsat landcover classification dataset with an overall classification accuracy of over 90%. Through extensive experiments, compared with the mainstream semantic segmentation methods, our proposed multi-temporal network achieves state-of-the-art performance with good robustness and generalization ability. Full article

(This article belongs to the Special Issue Land Use Classification with GIS and Remote Sensing Data Based on AI Technology)

► Show Figures

Figure 1

21 pages, 5848 KiB

Open AccessArticle

A Combined Convolutional Neural Network for Urban Land-Use Classification with GIS Data

by Jie Yu, Peng Zeng, Yaying Yu, Hongwei Yu, Liang Huang and Dongbo Zhou

Remote Sens. 2022, 14(5), 1128; https://0-doi-org.brum.beds.ac.uk/10.3390/rs14051128 - 24 Feb 2022

Cited by 15 | Viewed by 3002

Abstract

The classification of urban land-use information has become the underlying database for a variety of applications including urban planning and administration. The lack of datasets and changeable semantics of land-use make deep learning methods suffer from low precision, which prevent improvements in the effectiveness of using AI methods for applications. In this paper, we first used GIS data to produce a well-tagged and high-resolution urban land-use image dataset. Then, we proposed a combined convolutional neural network named DUA-Net for complex and diverse urban land-use classification. The DUA-Net combined U-Net and Densely connected Atrous Spatial Pyramid Pooling (DenseASPP) to extract Remote Sensing Imagers (RSIs) features in parallel. Then, channel attention was used to efficiently fuse the multi-source semantic information from the output of the double-layer network to learn the association between different land-use types. Finally, land-use classification of high-resolution urban RSIs was achieved. Experiments were performed on the dataset of this paper, the publicly available Vaihingen dataset and Potsdam dataset with overall accuracy levels reaching 75.90%, 89.71% and 89.91%, respectively. The results indicated that the complex land-use types with heterogeneous features were more difficult to extract than the single-feature land-cover types. The proposed DUA-Net method proved suitable for high-precision urban land-use classification, which will be of great value for urban planning and national land resource surveying. Full article

(This article belongs to the Special Issue Land Use Classification with GIS and Remote Sensing Data Based on AI Technology)

► Show Figures

Figure 1

22 pages, 4824 KiB

Open AccessArticle

Enhancing the Accuracy and Temporal Transferability of Irrigated Cropping Field Classification Using Optical Remote Sensing Imagery

by Zitian Gao, Danlu Guo, Dongryeol Ryu and Andrew W. Western

Remote Sens. 2022, 14(4), 997; https://0-doi-org.brum.beds.ac.uk/10.3390/rs14040997 - 18 Feb 2022

Cited by 3 | Viewed by 2405

Abstract

Mapping irrigated areas using remotely sensed imagery has been widely applied to support agricultural water management; however, accuracy is often compromised by the in-field heterogeneity of and interannual variability in crop conditions. This paper addresses these key issues. Two classification methods were employed to map irrigated fields using normalized difference vegetation index (NDVI) values derived from Landsat 7 and Landsat 8: a dynamic thresholding method (method one) and a random forest method (method two). To improve the representativeness of field-level NDVI aggregates, which are the key inputs in our methods, a Gaussian mixture model (GMM)-based filtering approach was adopted to remove noncrop pixels (e.g., trees and bare soils) and mixed pixels along the field boundary. To improve the temporal transferability of method one we dynamically determined the threshold value to account for the impact of interannual weather variability based on the dynamic range of NDVI values. In method two an innovative training sample pool was designed for the random forest modeling to enable automatic calibration for each season, which contributes to consistent performance across years. The irrigated field mapping was applied to a major irrigation district in Australia from 2011 to 2018, for summer and winter cropping seasons separately. The results showed that using GMM-based filtering can markedly improve field-level data quality and avoid up to 1/3 of omission errors for irrigated fields. Method two showed superior performance, exhibiting consistent and good accuracy (kappa > 0.9) for both seasons. The classified maps in wet winter seasons should be used with caution, because rainfall alone can largely meet plant water requirements, leaving the contribution of irrigation to the surface spectral signature weak. The approaches introduced are transferable to other areas, can support multiyear irrigated area mapping with high accuracy, and significantly reduced model development effort. Full article

(This article belongs to the Special Issue Land Use Classification with GIS and Remote Sensing Data Based on AI Technology)

► Show Figures

Figure 1

22 pages, 8931 KiB

Open AccessArticle

Automated School Location Mapping at Scale from Satellite Imagery Based on Deep Learning

by Iyke Maduako, Zhuangfang Yi, Naroa Zurutuza, Shilpa Arora, Christopher Fabian and Do-Hyung Kim

Remote Sens. 2022, 14(4), 897; https://0-doi-org.brum.beds.ac.uk/10.3390/rs14040897 - 13 Feb 2022

Cited by 4 | Viewed by 4328

Abstract

Computer vision for large scale building detection can be very challenging in many environments and settings even with recent advances in deep learning technologies. Even more challenging is modeling to detect the presence of specific buildings (in this case schools) in satellite imagery at a global scale. However, despite the variation in school building structures from rural to urban areas and from country to country, many school buildings have identifiable overhead signatures that make them possible to be detected from high-resolution imagery with modern deep learning techniques. Our hypothesis is that a Deep Convolutional Neural Network (CNN) could be trained for successful mapping of school locations at a regional or global scale from high-resolution satellite imagery. One of the key objectives of this work is to explore the possibility of having a scalable model that can be used to map schools across the globe. In this work, we developed AI-assisted rapid school location mapping models in eight countries in Asia, Africa, and South America. The results show that regional models outperform country-specific models and the global model. This indicates that the regional model took the advantage of having been exposed to diverse school location structure and features and generalized better, however, the global model was the worst performer due to the difficulty of generalizing the significant variability of school location features across different countries from different regions. Full article

(This article belongs to the Special Issue Land Use Classification with GIS and Remote Sensing Data Based on AI Technology)

► Show Figures

Graphical abstract

29 pages, 12082 KiB

Open AccessArticle

LPIN: A Lightweight Progressive Inpainting Network for Improving the Robustness of Remote Sensing Images Scene Classification

by Weining An, Xinqi Zhang, Hang Wu, Wenchang Zhang, Yaohua Du and Jinggong Sun

Remote Sens. 2022, 14(1), 53; https://0-doi-org.brum.beds.ac.uk/10.3390/rs14010053 - 23 Dec 2021

Cited by 3 | Viewed by 3201

Abstract

At present, the classification accuracy of high-resolution Remote Sensing Image Scene Classification (RSISC) has reached a quite high level on standard datasets. However, when coming to practical application, the intrinsic noise of satellite sensors and the disturbance of atmospheric environment often degrade real Remote Sensing (RS) images. It introduces defects to them, which affects the performance and reduces the robustness of RSISC methods. Moreover, due to the restriction of memory and power consumption, the methods also need a small number of parameters and fast computing speed to be implemented on small portable systems such as unmanned aerial vehicles. In this paper, a Lightweight Progressive Inpainting Network (LPIN) and a novel combined approach of LPIN and the existing RSISC methods are proposed to improve the robustness of RSISC tasks and satisfy the requirement of methods on portable systems. The defects in real RS images are inpainted by LPIN to provide a purified input for classification. With the combined approach, the classification accuracy on RS images with defects can be improved to the original level of those without defects. The LPIN is designed on the consideration of lightweight model. Measures are adopted to ensure a high gradient transmission efficiency while reducing the number of network parameters. Multiple loss functions are used to get reasonable and realistic inpainting results. Extensive tests of image inpainting of LPIN and classification tests with the combined approach on NWPU-RESISC45, UC Merced Land-Use and AID datasets are carried out which indicate that the LPIN achieves a state-of-the-art inpainting quality with less parameters and a faster inpainting speed. Furthermore, the combined approach keeps the comparable classification accuracy level on RS images with defects as that without defects, which will improve the robustness of high-resolution RSISC tasks. Full article

(This article belongs to the Special Issue Land Use Classification with GIS and Remote Sensing Data Based on AI Technology)

► Show Figures

Graphical abstract

26 pages, 6427 KiB

Open AccessArticle

An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image Classification

by Munirah Alkhelaiwi, Wadii Boulila, Jawad Ahmad, Anis Koubaa and Maha Driss

Remote Sens. 2021, 13(11), 2221; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13112221 - 06 Jun 2021

Cited by 55 | Viewed by 5795

Abstract

Satellite images have drawn increasing interest from a wide variety of users, including business and government, ever since their increased usage in important fields ranging from weather, forestry and agriculture to surface changes and biodiversity monitoring. Recent updates in the field have also introduced various deep learning (DL) architectures to satellite imagery as a means of extracting useful information. However, this new approach comes with its own issues, including the fact that many users utilize ready-made cloud services (both public and private) in order to take advantage of built-in DL algorithms and thus avoid the complexity of developing their own DL architectures. However, this presents new challenges to protecting data against unauthorized access, mining and usage of sensitive information extracted from that data. Therefore, new privacy concerns regarding sensitive data in satellite images have arisen. This research proposes an efficient approach that takes advantage of privacy-preserving deep learning (PPDL)-based techniques to address privacy concerns regarding data from satellite images when applying public DL models. In this paper, we proposed a partially homomorphic encryption scheme (a Paillier scheme), which enables processing of confidential information without exposure of the underlying data. Our method achieves robust results when applied to a custom convolutional neural network (CNN) as well as to existing transfer learning methods. The proposed encryption scheme also allows for training CNN models on encrypted data directly, which requires lower computational overhead. Our experiments have been performed on a real-world dataset covering several regions across Saudi Arabia. The results demonstrate that our CNN-based models were able to retain data utility while maintaining data privacy. Security parameters such as correlation coefficient (−0.004), entropy (7.95), energy (0.01), contrast (10.57), number of pixel change rate (4.86), unified average change intensity (33.66), and more are in favor of our proposed encryption scheme. To the best of our knowledge, this research is also one of the first studies that applies PPDL-based techniques to satellite image data in any capacity. Full article

(This article belongs to the Special Issue Land Use Classification with GIS and Remote Sensing Data Based on AI Technology)

► Show Figures

Figure 1

Other

Jump to: Research

20 pages, 9646 KiB

Open AccessTechnical Note

Bias in Deep Neural Networks in Land Use Characterization for International Development

by Do-Hyung Kim, Guzmán López, Diego Kiedanski, Iyke Maduako, Braulio Ríos, Alan Descoins, Naroa Zurutuza, Shilpa Arora and Christopher Fabian

Remote Sens. 2021, 13(15), 2908; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13152908 - 24 Jul 2021

Cited by 3 | Viewed by 3843

Abstract

Understanding the biases in Deep Neural Networks (DNN) based algorithms is gaining paramount importance due to its increased applications on many real-world problems. A known problem of DNN penalizing the underrepresented population could undermine the efficacy of development projects dependent on data produced using DNN-based models. In spite of this, the problems of biases in DNN for Land Use and Land Cover Classification (LULCC) have not been a subject of many studies. In this study, we explore ways to quantify biases in DNN for land use with an example of identifying school buildings in Colombia from satellite imagery. We implement a DNN-based model by fine-tuning an existing, pre-trained model for school building identification. The model achieved overall 84% accuracy. Then, we used socioeconomic covariates to analyze possible biases in the learned representation. The retrained deep neural network was used to extract visual features (embeddings) from satellite image tiles. The embeddings were clustered into four subtypes of schools, and the accuracy of the neural network model was assessed for each cluster. The distributions of various socioeconomic covariates by clusters were analyzed to identify the links between the model accuracy and the aforementioned covariates. Our results indicate that the model accuracy is lowest (57%) where the characteristics of the landscape are predominantly related to poverty and remoteness, which confirms our original assumption on the heterogeneous performances of Artificial Intelligence (AI) algorithms and their biases. Based on our findings, we identify possible sources of bias and present suggestions on how to prepare a balanced training dataset that would result in less biased AI algorithms. The framework used in our study to better understand biases in DNN models would be useful when Machine Learning (ML) techniques are adopted in lieu of ground-based data collection for international development programs. Because such programs aim to solve issues of social inequality, MLs are only applicable when they are transparent and accountable. Full article

(This article belongs to the Special Issue Land Use Classification with GIS and Remote Sensing Data Based on AI Technology)

► Show Figures