Submit to Applied Sciences Review for Applied Sciences Propose a Special Issue

Journal Browser

► Journal Browser

Geospatial AI in Earth Observation, Remote Sensing and GIScience

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

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Earth Sciences".

Deadline for manuscript submissions: closed (13 January 2024) | Viewed by 10569

Share This Special Issue

Special Issue Editors

Dr. Shan Liu

E-Mail Website
Guest Editor

School of Automation, University of Electronic Science and Technology of China, Chengdu 610054, China
Interests: artificial intelligence; intelligent transportation
Special Issues, Collections and Topics in MDPI journals

Dr. Kenan Li

E-Mail Website
Guest Editor

Department of Epidemiology and Biostatistics, College of Public Health and Social Justice, Saint Louis University, St. Louis, MO 63103, USA
Interests: geoinformatics; spatial computation and modeling of community resilience/sustainability; data science and statistics in land use; geo-simulation of human and environmental systems; GeoAI (artificial intelligence) frameworks; integrated geo-cyber-infrastructures; urban planning; GIS/RS; AI/ML; social equity; land development; urbanization; space value modelling; social sensing; GeoAI; land management; land policy
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Xuan Liu

E-Mail Website
Guest Editor

School of Public Affairs and Administration, University of Electronic Science and Technology of China, Chengdu 610054, China
Interests: geoInformatics; urban planning; urban renewal; real estate; GIS/RS; AI/ML; social equity; land development; urbanization; space value modelling; post-productivism transformation; social sensing; GeoAI; land management; land policy
Special Issues, Collections and Topics in MDPI journals

Dr. Zhengtong Yin

E-Mail Website
Guest Editor

College of Resource and Environment Engineering, Guizhou University, Guiyang, China
Interests: AI/ML; complex dynamics; pattern recognition; visual reasoning; visual question answering; NLP; surgical robot; geospatial AI; GIS/RS; image fusion; surgical vision; 3D visualization; artificial neural network; computer graphics; image processing; machine vision; 3D reconstruction; medical imaging; data mining; earth surface process; cloud computing; geography and environmental science
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Geospatial Artificial Intelligence (Geospatial AI) approaches have had a transformative influence in earth observation and remote sensing fields such as nature language processing and computer vision. With the progressions of deep learning algorithms, software and hardware technologies, scalable computation platforms, and the availability of high-resolution geospatial data are empowering the fast-growing field of Geospatial AI. These state-of-the-art methods have enabled a next generation of earth observation and remote sensing and provided new means for researching the earth’s surface at a variety of scales from land use changes to other geographic forms and processes in general. Moreover, in the past few decades, to capture the dynamic process of space change which is often driven by the combination of synergetic spatial and aspatial factors and their interactions, researchers had made great efforts to unravel the mechanism behind it. The great strides in complex analysis and Geospatial AI in spatial analysis fundamentally changed the traditional methodologies and provided deeper theoretical insight into the dynamics of space change.

Geospatial AI emphasizes the cognition of the geographical environment and enriches GIScience by integrating multi-angle, multi-spectrum, multi-platform, multi-scale data. Meanwhile, although the multi-modal remote sensing data fusion can break through the limitation of single-modal data, eliminate redundancy, and achieve effective combination and utilization of complementary information, multi-modal AI structures require huge computational cost. Thus, simulating reality with data-driven machine learning within a relatively simple framework is desired. To a large extent, modern Geospatial AI systems do not only establish assumptions and structured concepts about the operating principles of the world but also tend to minimize the structure of algorithms to preserve the simplicity of the algorithm and explain complex scenes on the earth’s surface. Further studies require the combination of macroscopic geographic zoning deconstruction and microscopic visual cognition to develop complexity metrics and form multi-scale adaptive schemes. More practices are needed to reveal the application fields of different AI algorithms.

With this Special Issue, we try to inspire the growth and distribution of open Geospatial AI tools that can be re-processed for GIScience research and education. Submissions demonstrating the added value of taking a Geospatial AI approach over existing approaches would be preferred. Papers should ideally also allow insights into mechanistic underpinnings of the system being investigated. New theories and methods of AI applications in spatially explicit AI models, spatial prediction and interpolation, earth observation, social sensing, and geospatial semantics are all welcomed by this Special Issue. Potential topics in this collection include but are not limited to the following topics:

Geospatial AI for object detection, localization, and classification.
Geospatial AI for agent-based modeling and cellular automata.
Geospatial AI for object segmentation, reconstruction, and registration.
Geospatial AI for anomaly/novelty detection and visual search.
Geospatial AI for using light detection and range (LiDAR) data.
Geospatial AI for developing early warning systems.
Geospatial AI for Climate Trace.
Geospatial AI for environmental watch such as biomass watch, fishing watch, forest watch and beyond.
Geospatial AI for generating new geo-spatial datasets in earth domain.
Geospatial AI for smart conveyance, autonomous cars.
Geospatial AI for all other earth observation applications.
Geospatial AI for modeling land use and land cover changes.

Dr. Shan Liu
Dr. Kenan Li
Prof. Dr. Xuan Liu
Dr. Zhengtong Yin
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. Applied Sciences 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 2400 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

geospatial AI for object detection, localization, and classification
geospatial AI for agent-based modeling and cellular automata
geospatial AI for object segmentation, reconstruction, and registration
geospatial AI for anomaly/novelty detection and visual search
geospatial AI for using light detection and range (LiDAR) data
geospatial AI for developing early warning systems
geospatial AI for climate trace
geospatial AI for environmental watch such as biomass watch, fishing watch, forest watch and beyond
geospatial AI for generating new geo-spatial datasets in earth domain
geospatial AI for smart conveyance, autonomous cars
geospatial AI for all other earth observation applications
geospatial AI for modeling land use and land cover changes

Published Papers (7 papers)

Download All Papers

Editorial

Jump to: Research

3 pages, 166 KiB

Open AccessEditorial

Geospatial AI in Earth Observation, Remote Sensing, and GIScience

by Shan Liu, Kenan Li, Xuan Liu and Zhengtong Yin

Appl. Sci. 2023, 13(22), 12203; https://doi.org/10.3390/app132212203 - 10 Nov 2023

Viewed by 1036

Abstract

Geospatial artificial intelligence (Geo-AI) methods have revolutionarily impacted earth observation and remote sensing [...] Full article

(This article belongs to the Special Issue Geospatial AI in Earth Observation, Remote Sensing and GIScience)

Research

Jump to: Editorial

18 pages, 14499 KiB

Open AccessArticle

Validation Analysis of Drought Monitoring Based on FY-4 Satellite

by Han Luo, Zhengjiang Ma, Huanping Wu, Yonghua Li, Bei Liu, Yuxia Li and Lei He

Appl. Sci. 2023, 13(16), 9122; https://doi.org/10.3390/app13169122 - 10 Aug 2023

Cited by 1 | Viewed by 982

Abstract

Droughts are natural disasters that have significant implications for agricultural production and human livelihood. Under climate change, the drought process is accelerating, such as the intensification of flash droughts. The efficient and quick monitoring of droughts has increasingly become a crucial measure in responding to extreme drought events. We utilized multi-imagery data from the geostationary meteorological satellite FY-4A within one day; implemented the daily Maximum Value Composite (MVC) method to minimize interference from the clouds, atmosphere, and anomalies; and developed a method for calculating the daily-scale Temperature Vegetation Drought Index (TVDI), which is a dryness index. Three representative drought events (Yunnan Province, Guangdong Province, and the Huanghuai region) from 2021 to 2022 were selected for validation, respectively. We evaluated the spatial and temporal effects of the TVDI with the Soil Relative Humidity Index (SRHI) and the Meteorological Drought Composite Index (MCI). The results show that the TVDI has stronger negative correlations with the MCI and SRHI in moderate and severe drought events. Meanwhile, the TVDI and SRHI exhibited similar trends. The trends of drought areas identified by the TVDI, SRHI, and MCI were consistent, while the drought area identified by the TVDI was slightly higher than the SRHI. Yunnan Province has the most concentrated distribution, which is mostly between 16.93 and 25.22%. The spatial distribution of the TVDI by FY-4A and MODIS is generally consistent, and the differences in severe drought areas may be attributed to disparities in the NDVI. Furthermore, the TVDI based on FY-4A provides a higher number of valid pixels (437 more pixels in the Huanghuai region) than that based on MODIS, yielding better overall drought detection. The spatial distribution of the TVDI between FY-4A and Landsat-8 is also consistent. FY-4A has the advantage of acquiring a complete image on a daily basis, and lower computational cost in regional drought monitoring. The results indicate the effectiveness of the FY-4A TVDI in achieving daily-scale drought monitoring, with a larger number of valid pixels and better spatial consistency with station indices. This study provides a new solution for drought monitoring using a geostationary meteorological satellite from different spatial–temporal perspectives to facilitate comprehensive drought monitoring. Full article

(This article belongs to the Special Issue Geospatial AI in Earth Observation, Remote Sensing and GIScience)

► Show Figures

Figure 1

17 pages, 9349 KiB

Open AccessArticle

A Lightweight and Partitioned CNN Algorithm for Multi-Landslide Detection in Remote Sensing Images

by Peijun Mo, Dongfen Li, Mingzhe Liu, Jiaru Jia and Xin Chen

Appl. Sci. 2023, 13(15), 8583; https://doi.org/10.3390/app13158583 - 25 Jul 2023

Cited by 4 | Viewed by 1236

Abstract

Landslide detection is crucial for natural disaster risk management. Deep-learning-based object-detection algorithms have been shown to be effective in landslide studies. However, advanced algorithms currently used for landslide detection require high computational complexity and memory requirements, limiting their practical applicability. In this study, we developed a high-resolution dataset for landslide-prone regions in China by extracting historical landslide remote sensing images from the Google Earth platform. We propose a lightweight LP-YOLO algorithm based on YOLOv5, with a more-lightweight backbone that incorporates our designed PartitionNet and neck equipped with CSPCrossStage. We constructed and added the vertical and horizontal (VH) block to the backbone, which explores and aggregates long-range information with two directions, while consuming a small amount of computational cost. A new feature fusion structure is proposed to boost information flow and enhance the location accuracy. To speed up the model learning process and improve the accuracy, the SCYLLA-IoU (SIoU) bounding box regression loss function was used to replace the complete IoU (CIoU) loss function. The experimental results demonstrated that our proposed model achieved the highest detection performance (53.7% of Precision, 49% of AP50 and 25.5% of AP50:95) with a speed of 74 fps. Compared to the YOLOv5 model, the proposed model achieved 4% improvement for Precision, 2.6% improvement for AP50, and 2.5% for AP50:95, while reducing the model parameters and FLOPs by 38.4% and 53.1%, respectively. The results indicated that the proposed lightweight method provides a technical guidance for achieving reliable and real-time automatic landslide detection and can be used for disaster prevention and mitigation. Full article

(This article belongs to the Special Issue Geospatial AI in Earth Observation, Remote Sensing and GIScience)

► Show Figures

Figure 1

16 pages, 4234 KiB

Open AccessArticle

Hydropower Functional Zoning with Crowdsourced Geospatial Data: A Case Study in Sichuan Province

by Li Ju, Maosheng Luo, Han Luo, Zelong Ma, Xiping Lu and Guoxin Jiang

Appl. Sci. 2023, 13(12), 7260; https://doi.org/10.3390/app13127260 - 18 Jun 2023

Cited by 1 | Viewed by 988

Abstract

Hydro-electric development has received increasing attention due to its characteristics of ecological and environmental protection. In addition, aquatic ecological functional zoning plays a key role in the aquatic ecological management in the basin because of its ecological background and basic unit. However, hydropower function has seldom been considered in aquatic ecological functional zoning. This research proposes a framework for hydropower functional zoning on the aquatic-and-terrestrial-coupled ecosystem function with crowdsourced geospatial data and the spatial-clustering method. Sichuan Province was selected as the research area due to its critical hydroelectric position in China, and it is divided into 53 level 3 zones, 27 level 2 aquatic ecological functional zones, and 17 level 1 ecological functional zones. Focusing on the results of the hydropower functional zoning, the ecological-environmental problem of each zoning and the hydroelectric development in the future are discussed. The soil-erosion area in Sichuan Province did not overlap with the hydroelectric-construction-affected zones. Further, water pollution occurred in construction zones and core affected zones of the Fu River Basin and the Jialing River Basin. In the next 10 years, the middle and upper reaches of the trunk of the Ya-lung River will become key areas for hydropower-engineering projects. This research provides new insight into the development of various regional hydropower projects and the sustainable management of watersheds, which is helpful for the construction of new hydroelectric-energy development. Full article

(This article belongs to the Special Issue Geospatial AI in Earth Observation, Remote Sensing and GIScience)

► Show Figures

Figure 1

18 pages, 3997 KiB

Open AccessArticle

Analysis and Evaluation of Extreme Rainfall Trends and Geological Hazards Risk in the Lower Jinshajiang River

by Xiaojia Bi, Qiang Fan, Lei He, Cunjie Zhang, Yifei Diao and Yanlin Han

Appl. Sci. 2023, 13(6), 4021; https://doi.org/10.3390/app13064021 - 22 Mar 2023

Cited by 6 | Viewed by 1652

Abstract

This research studied the risk assessment of geological hazards, such as landslides and debris flow, under the time series and trend characteristics of extreme precipitation events in the last 60 years in nine typical regions of the lower Jinshajiang River Basin. Nine indicators, including slope, engineering geological rock group, slope structure type, distance to road, topographic relief, distance to fault, distance to the water system, vegetation cover and profile curvature, were selected as the index factors for landslide susceptibility evaluation, and the information quantity method was used to obtain the landslide susceptibility evaluation of the study area. Based on the susceptibility evaluation, the spatial analysis function of GIS was used to derive the geological hazard zoning under the extreme rainfall trend. The results showed that the areas with high extreme rainfall trends have higher densities of geological hazard development and they are concentrated, while areas with low extreme rainfall trends have relatively less geological hazard development, and what development exists is scattered. Full article

(This article belongs to the Special Issue Geospatial AI in Earth Observation, Remote Sensing and GIScience)

► Show Figures

Figure 1

16 pages, 4112 KiB

Open AccessArticle

Atmospheric Density Inversion Based on Swarm-C Satellite Accelerometer

by Lirong Yin, Lei Wang, Jiawei Tian, Zhengtong Yin, Mingzhe Liu and Wenfeng Zheng

Appl. Sci. 2023, 13(6), 3610; https://doi.org/10.3390/app13063610 - 11 Mar 2023

Cited by 26 | Viewed by 1615

Abstract

We used the Swarm-C accelerometer data to invert the orbital atmospheric density in this study. First, the Swarm-C satellite mission data were obtained from the ESA’s public data platform, and preliminary data error correction was performed. This paper refers to the calibration method of GRACE-A satellite accelerometer data. It adds linear temperature correction on the original basis. Moreover, this study’s accelerometer data correction results were compared with the data correction results published by the ESA. In order to explore the influence of light radiation on the accelerometer, we established a geometric model of Swarm-C to simulate the physical shape of the satellite surface. The light radiation pressure model and the shadow area judgment model were established, the change in the light radiation acceleration during the transition process of the satellite from the umbra area to the penumbra area and then to the shadowless area was studied, and the state transition during the transition process was analyzed. Finally, the atmospheric drag coefficient was calculated based on the Sentman model. Atmospheric density inversion calculations were performed using the above data. We show the spatial distribution of atmospheric density at a fixed latitude, testing our results during geomagnetic storms. We compared the density results with existing research data, demonstrating the effectiveness of our approach. Full article

(This article belongs to the Special Issue Geospatial AI in Earth Observation, Remote Sensing and GIScience)

► Show Figures

Figure 1

15 pages, 2968 KiB

Open AccessArticle

Geographic Variations in Human Mobility Patterns during the First Six Months of the COVID-19 Pandemic in California

by Kenan Li, Sandrah P. Eckel, Erika Garcia, Zhanghua Chen, John P. Wilson and Frank D. Gilliland

Appl. Sci. 2023, 13(4), 2440; https://doi.org/10.3390/app13042440 - 14 Feb 2023

Cited by 2 | Viewed by 1508

Abstract

Human mobility influenced the spread of the COVID-19 virus, as revealed by the high spatiotemporal granularity location service data gathered from smart devices. We conducted time series clustering analysis to delineate the relationships between human mobility patterns (HMPs) and their social determinants in California (CA) using aggregated smart device tracking data from SafeGraph. We first identified four types of temporal patterns for five human mobility indicator changes by applying dynamic-time-warping self-organizing map clustering methods. We then performed an analysis of variance and linear discriminant analysis on the HMPs with 17 social, economic, and demographic variables. Asians, children under five, adults over 65, and individuals living below the poverty line were found to be among the top contributors to the HMPs, including the HMP with a significant increase in the median home dwelling time and the HMP with emerging weekly patterns in full-time and part-time work devices. Our findings show that the CA shelter-in-place policy had varying impacts on HMPs, with socially disadvantaged places showing less compliance. The HMPs may help practitioners to anticipate the efficacy of non-pharmaceutical interventions on cases and deaths in pandemics. Full article

(This article belongs to the Special Issue Geospatial AI in Earth Observation, Remote Sensing and GIScience)

► Show Figures