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

Journal Menu

Journal Browser

Advancing Machine Learning for Remote Sensing to Enhance Spatio-Temporal Generalizability

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 "Remote Sensing in Geology, Geomorphology and Hydrology".

Deadline for manuscript submissions: 30 April 2024 | Viewed by 9792

Share This Special Issue

Special Issue Editors

Dr. Xiaowei Jia

E-Mail Website
Guest Editor

Department of Computer Science, University of Pittsburgh, Pittsburgh, PA, USA
Interests: knowledge-guided machine learning; spatiotemporal data mining; deep learning

Dr. Kuishuang Feng

E-Mail Website
Guest Editor

Department of Geographical Sciences, University of Maryland, College Park, MD 20742, USA
Interests: spatial ecological-economic modeling; sustainable production and consumption; scenario analysis; evaluation of environmental issues
Special Issues, Collections and Topics in MDPI journals

Dr. Yiqun Xie

E-Mail Website
Guest Editor

Geospatial Information Science, University of Maryland, College Park, MD, USA
Interests: spatial data science; artificial intelligence

Special Issue Information

Dear Colleagues,

With the impact of climate change and a growing population, human society is facing increasing environmental crises, including extreme weather events (droughts, floods, forest fires), rising sea levels, and a reduction in the security of food and water. With an increasing amount of available spatiotemporal big data collected from remote sensing (e.g., spaceborne and airbone imagery), machine learning methods provide tremendous opportunities in addressing these grand challenges. Despite the recent success of machine learning and deep learning in various computer vision and natural language processing tasks, these models often fall short in generalizing over space and time due to the variability of data distribution and data quantity in remote sensing data.

For this Special Issue, we invite the submission of articles on recent advances in machine learning for enhancing the generalizability of using remote sensing data over space and time. This includes applications and new algorithms of advanced machine learning techniques with regard to remote sensing, e.g., meta-learning, domain adaptation, knowledge-guided machine learning, online learning, and self-supervised learning. Societally important remote sensing applications that study agriculture, hydrology, transportation, and urbanization using spatiotemporal deep learning models are also welcome for submission.

The potential topics may include, but are not limited to:

Meta-learning for model adaptation over space and time.
Statistical machine learning for analyzing and addressing spatial and temporal data variability.
Knowledge-guided machine learning on remote sensing for improving performance under data-scarce and out-of-distribution scenarios.
Domain adaptation techniques for reducing distributional gaps.
Online learning and continual learning for temporal model updates.
Self-supervised and pre-training techniques on remote sensing.
Enforcing fairness over space and time for machine learning models on remote sensing.
Spatiotemporal deep learning models that are scalable to large regions.
Remote sensing applications over large regions in agriculture, hydrology, urbanization, forestry, transportation, etc.

Dr. Xiaowei Jia
Dr. Kuishuang Feng
Dr. Yiqun Xie
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

deep learning
model generalizability
spatial-aware learning
fairness
meta learning
spatiotemporal deep learning
knowledge-guided machine learning

Published Papers (6 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

17 pages, 5786 KiB

Open AccessArticle

Segment Anything Model Can Not Segment Anything: Assessing AI Foundation Model’s Generalizability in Permafrost Mapping

by Wenwen Li, Chia-Yu Hsu, Sizhe Wang, Yezhou Yang, Hyunho Lee, Anna Liljedahl, Chandi Witharana, Yili Yang, Brendan M. Rogers, Samantha T. Arundel, Matthew B. Jones, Kenton McHenry and Patricia Solis

Remote Sens. 2024, 16(5), 797; https://doi.org/10.3390/rs16050797 - 24 Feb 2024

Viewed by 1662

Abstract

This paper assesses trending AI foundation models, especially emerging computer vision foundation models and their performance in natural landscape feature segmentation. While the term foundation model has quickly garnered interest from the geospatial domain, its definition remains vague. Hence, this paper will first introduce AI foundation models and their defining characteristics. Built upon the tremendous success achieved by Large Language Models (LLMs) as the foundation models for language tasks, this paper discusses the challenges of building foundation models for geospatial artificial intelligence (GeoAI) vision tasks. To evaluate the performance of large AI vision models, especially Meta’s Segment Anything Model (SAM), we implemented different instance segmentation pipelines that minimize the changes to SAM to leverage its power as a foundation model. A series of prompt strategies were developed to test SAM’s performance regarding its theoretical upper bound of predictive accuracy, zero-shot performance, and domain adaptability through fine-tuning. The analysis used two permafrost feature datasets, ice-wedge polygons and retrogressive thaw slumps because (1) these landform features are more challenging to segment than man-made features due to their complicated formation mechanisms, diverse forms, and vague boundaries; (2) their presence and changes are important indicators for Arctic warming and climate change. The results show that although promising, SAM still has room for improvement to support AI-augmented terrain mapping. The spatial and domain generalizability of this finding is further validated using a more general dataset EuroCrops for agricultural field mapping. Finally, we discuss future research directions that strengthen SAM’s applicability in challenging geospatial domains. Full article

(This article belongs to the Special Issue Advancing Machine Learning for Remote Sensing to Enhance Spatio-Temporal Generalizability)

► Show Figures

Figure 1

17 pages, 2993 KiB

Open AccessArticle

Reconstruction of Continuous High-Resolution Sea Surface Temperature Data Using Time-Aware Implicit Neural Representation

by Yang Wang, Hassan A. Karimi and Xiaowei Jia

Remote Sens. 2023, 15(24), 5646; https://doi.org/10.3390/rs15245646 - 06 Dec 2023

Viewed by 962

Abstract

Accurate climate data at fine spatial resolution are essential for scientific research and the development and planning of crucial social systems, such as energy and agriculture. Among them, sea surface temperature plays a critical role as the associated El Niño–Southern Oscillation (ENSO) is considered a significant signal of the global interannual climate system. In this paper, we propose an implicit neural representation-based interpolation method with temporal information (

T_I N R I

) to reconstruct climate data of high spatial resolution, with sea surface temperature as the research object. Traditional deep learning models for generating high-resolution climate data are only applicable to fixed-resolution enhancement scales. In contrast, the proposed

T_I N R I

method is not limited to the enhancement scale provided during the training process and its results indicate that it can enhance low-resolution input by arbitrary scale. Additionally, we discuss the impact of temporal information on the generation of high-resolution climate data, specifically, the influence of the month from which the low-resolution sea surface temperature data are obtained. Our experimental results indicate that

T_I N R I

is advantageous over traditional interpolation methods under different enhancement scales, and the temporal information can improve

T_I N R I

performance for a different calendar month. We also examined the potential capability of

T_I N R I

in recovering missing grid value. These results demonstrate that the proposed

T_I N R I

is a promising method for generating high-resolution climate data and has significant implications for climate research and related applications. Full article

(This article belongs to the Special Issue Advancing Machine Learning for Remote Sensing to Enhance Spatio-Temporal Generalizability)

► Show Figures

Figure 1

22 pages, 4545 KiB

Open AccessArticle

MFTSC: A Semantically Constrained Method for Urban Building Height Estimation Using Multiple Source Images

by Yuhan Chen, Qingyun Yan and Weimin Huang

Remote Sens. 2023, 15(23), 5552; https://doi.org/10.3390/rs15235552 - 29 Nov 2023

Cited by 4 | Viewed by 885

Abstract

The use of remote sensing imagery has significantly enhanced the efficiency of building extraction; however, the precise estimation of building height remains a formidable challenge. In light of ongoing advancements in computer vision, numerous techniques leveraging convolutional neural networks and Transformers have been applied to remote sensing imagery, yielding promising outcomes. Nevertheless, most existing approaches directly estimate height without considering the intrinsic relationship between semantic building segmentation and building height estimation. In this study, we present a unified architectural framework that integrates the tasks of building semantic segmentation and building height estimation. We introduce a Transformer model that systematically merges multi-level features with semantic constraints and leverages shallow spatial detail feature cues in the encoder. Our approach excels in both height estimation and semantic segmentation tasks. Specifically, the coefficient of determination (

R^{2}

) in the height estimation task attains a remarkable 0.9671, with a root mean square error (RMSE) of 1.1733 m. The mean intersection over union (mIoU) for building semantic segmentation reaches 0.7855. These findings underscore the efficacy of multi-task learning by integrating semantic segmentation with height estimation, thereby enhancing the precision of height estimation. Full article

(This article belongs to the Special Issue Advancing Machine Learning for Remote Sensing to Enhance Spatio-Temporal Generalizability)

► Show Figures

Figure 1

18 pages, 4932 KiB

Open AccessArticle

Cloud Removal in Remote Sensing Using Sequential-Based Diffusion Models

by Xiaohu Zhao and Kebin Jia

Remote Sens. 2023, 15(11), 2861; https://doi.org/10.3390/rs15112861 - 31 May 2023

Cited by 2 | Viewed by 1797

Abstract

The majority of the optical observations collected via spaceborne optical satellites are corrupted by clouds or haze, restraining further applications of Earth observation; thus, exploring an ideal method for cloud removal is of great concern. In this paper, we propose a novel probabilistic generative model named sequential-based diffusion models (SeqDMs) for the cloud-removal task in a remote sensing domain. The proposed method consists of multi-modal diffusion models (MmDMs) and a sequential-based training and inference strategy (SeqTIS). In particular, MmDMs is a novel diffusion model that reconstructs the reverse process of denosing diffusion probabilistic models (DDPMs) to integrate additional information from auxiliary modalities (e.g., synthetic aperture radar robust to the corruption of clouds) to help the distribution learning of main modality (i.e., optical satellite imagery). In order to consider the information across time, SeqTIS is designed to integrate temporal information across an arbitrary length of both the main modality and auxiliary modality input sequences without retraining the model again. With the help of MmDMs and SeqTIS, SeqDMs have the flexibility to handle an arbitrary length of input sequences, producing significant improvements only with one or two additional input samples and greatly reducing the time cost of model retraining. We evaluate our method on a public real-world dataset SEN12MS-CR-TS for a multi-modal and multi-temporal cloud-removal task. Our extensive experiments and ablation studies demonstrate the superiority of the proposed method on the quality of the reconstructed samples and the flexibility to handle arbitrary length sequences over multiple state-of-the-art cloud removal approaches. Full article

(This article belongs to the Special Issue Advancing Machine Learning for Remote Sensing to Enhance Spatio-Temporal Generalizability)

► Show Figures

Graphical abstract

20 pages, 3740 KiB

Open AccessArticle

Improvements in Forest Segmentation Accuracy Using a New Deep Learning Architecture and Data Augmentation Technique

by Yan He, Kebin Jia and Zhihao Wei

Remote Sens. 2023, 15(9), 2412; https://doi.org/10.3390/rs15092412 - 05 May 2023

Cited by 3 | Viewed by 1778

Abstract

Forests are critical to mitigating global climate change and regulating climate through their role in the global carbon and water cycles. Accurate monitoring of forest cover is, therefore, essential. Image segmentation networks based on convolutional neural networks have shown significant advantages in remote sensing image analysis with the development of deep learning. However, deep learning networks typically require a large amount of manual ground truth labels for training, and existing widely used image segmentation networks struggle to extract details from large-scale high resolution satellite imagery. Improving the accuracy of forest image segmentation remains a challenge. To reduce the cost of manual labelling, this paper proposed a data augmentation method that expands the training data by modifying the spatial distribution of forest remote sensing images. In addition, to improve the ability of the network to extract multi-scale detailed features and the feature information from the NIR band of satellite images, we proposed a high-resolution forest remote sensing image segmentation network by fusing multi-scale features based on double input. The experimental results using the Sanjiangyuan plateau forest dataset show that our method achieves an IoU of 90.19%, which outperforms prevalent image segmentation networks. These results demonstrate that the proposed approaches can extract forests from remote sensing images more effectively and accurately. Full article

(This article belongs to the Special Issue Advancing Machine Learning for Remote Sensing to Enhance Spatio-Temporal Generalizability)

► Show Figures

Graphical abstract

18 pages, 3378 KiB

Open AccessArticle

Upscaling of Latent Heat Flux in Heihe River Basin Based on Transfer Learning Model

by Jing Lin, Tongren Xu, Gangqiang Zhang, Xiangping He, Shaomin Liu, Ziwei Xu, Lifang Zhao, Zongbin Xu and Jiancheng Wang

Remote Sens. 2023, 15(7), 1901; https://doi.org/10.3390/rs15071901 - 01 Apr 2023

Viewed by 1389

Abstract

Latent heat flux (LE) plays an essential role in the hydrological cycle, surface energy balance, and climate change, but the spatial resolution of site-scale LE extremely limits its application potential over a regional scale. To overcome the limitation, five transfer learning models were constructed based on artificial neural networks (ANNs), random forests (RFs), extreme gradient boosting (XGBoost), support vector machine (SVM), and light gradient boosting machine (LightGBM) to upscale LE from site scale to regional scale in Heihe River basin (HRB). The instance-transfer approach that utilizes data samples outside of HRB was used in the transfer learning models. Moreover, the Bayesian-based three-cornered hat (BTCH) method was used to fuse the best three upscaling results from ANN, RF, and XGBoost models to improve the accuracy of the results. The results indicated that the transfer learning models perform best when the transfer ratio (the data samples ratio between external and HRB dataset) was 0.6. Specifically, the coefficient of determination (R²) and root mean squared errors (RMSE) of LE upscaled by ANN model was improved or reduced by 6% or 17% than the model without external data. Furthermore, the BTCH method can effectively improve the performance of single transfer learning model with the highest accuracy (R² = 0.83, RMSE = 18.84 W/m²). Finally, the LE upscaling model based on transfer learning model demonstrated great potential in HRB, which may be applicable to similar research in other regions. Full article

(This article belongs to the Special Issue Advancing Machine Learning for Remote Sensing to Enhance Spatio-Temporal Generalizability)

► Show Figures

Journal Menu

Journal Browser

Advancing Machine Learning for Remote Sensing to Enhance Spatio-Temporal Generalizability

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (6 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI