remotesensing-logo

Journal Browser

Journal Browser

Application of Artificial Intelligence in Land Use and Land Cover Mapping II

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

Deadline for manuscript submissions: closed (1 July 2024) | Viewed by 30654

Special Issue Editors


E-Mail Website
Guest Editor
1. Center for Geographic Information System, University of the Punjab, Lahore, Pakistan
2. Remote Sensing, GIS and Climatic Research Lab, National Center of GIS and Space Applications, University of the Punjab, Lahore, Pakistan
3. Department of Land Survying and Geo-Informatics, The Hong Kong Polytechnic, University, Hong Kong
Interests: earth obsersation and analytics; spatial data science; digital technologies; smart cities; environmental monitoring; landscape ecology; forest; urban ecologyurban climate; climate change; land-cover and land-use change; drought; cropland; air pollution; water quality; cloud computing; machine learning; big data for SDGs
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
International Centre for Integrated Mountain Development (ICIMOD), Kathmandu, Nepal
Interests: remote sensing; land degradation; croplands; droughts; environmental monitoring; machine learning
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Kunming Institute of Botany, Chinese Academy of Sciences, Kunming, China
Interests: land cover land use change; landscape restoration; biodiversity conservation
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Nexus of data analytics and computer vision with remote sensing data has revolutionised the information extraction of earth’s features. The rapid evolution of Artificial Intelligence and Earth Observation technologies is providing enhanced insights into landscape change and sustainable development. Land-use change data from satellite remote sensing, along with climate modelling and socio-economic indicators are playing vital roles in advancing interdisciplinary research. The huge amount of data currently produced by modern Earth Observation satellite missions and Unmanned Aerial Vehicles (UAVs), the availability of high-performance computing platforms and the development of Artificial Intelligence provide new opportunities to advance our knowledge about patterns of resource distribution and resource use. Machine learning approaches tailored for Earth Observation data can effectively support the challenges of spatial and temporal domain adaptation, hyperspectral data mining, integration of multi-source information and large-volume data analysis.

The previous special issue “Application of Artificial Intelligence in Land Use and Land Cover Mapping” was a great success. This indicates that the development of new approaches for information extraction from remote sensing data using Artificial Intelligence is incessant. Therefore, this second volume is launched aiming at collecting articles capitalizing on the integration of emerging remote sensing technologies and recent advances in computer vision and machine learning.

We welcome submissions that provide the community with the most recent advancements in all aspects mentioned above. We welcome, Original Research Articles, Reviews, Letters, and Technical Notes, as well as Highlight articles for a broader audience.

Dr. Sawaid Abbas
Prof. Dr. Jianchu Xu
Dr. Faisal M. Qamer
Prof. Dr. Janet E. Nichol
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

  • object detection in remote sensing images
  • dynamic features extraction
  • land cover
  • land use
  • monitoring change
  • urban morphology
  • hyperspectral mapping
  • machine learning and deep learning
  • pattern recognition and data mining
  • hyper-temporal mapping
  • biophysical and social data integration
  • sustainable development goals (SDGs)

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 (10 papers)

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

Research

20 pages, 4796 KiB  
Article
ABNet: An Aggregated Backbone Network Architecture for Fine Landcover Classification
by Bo Si, Zhennan Wang, Zhoulu Yu and Ke Wang
Remote Sens. 2024, 16(10), 1725; https://doi.org/10.3390/rs16101725 - 13 May 2024
Viewed by 1086
Abstract
High-precision landcover classification is a fundamental prerequisite for resource and environmental monitoring and land-use status surveys. Imbued with intricate spatial information and texture features, very high spatial resolution remote sensing images accentuate the divergence between features within the same category, thereby amplifying the [...] Read more.
High-precision landcover classification is a fundamental prerequisite for resource and environmental monitoring and land-use status surveys. Imbued with intricate spatial information and texture features, very high spatial resolution remote sensing images accentuate the divergence between features within the same category, thereby amplifying the complexity of landcover classification. Consequently, semantic segmentation models leveraging deep backbone networks have emerged as stalwarts in landcover classification tasks owing to their adeptness in feature representation. However, the classification efficacy of a solitary backbone network model fluctuates across diverse scenarios and datasets, posing a persistent challenge in the construction or selection of an appropriate backbone network for distinct classification tasks. To elevate the classification performance and bolster the generalization of semantic segmentation models, we propose a novel semantic segmentation network architecture, named the aggregated backbone network (ABNet), for the meticulous landcover classification. ABNet aggregates three prevailing backbone networks (ResNet, HRNet, and VoVNet), distinguished by significant structural disparities, using a same-stage fusion approach. Subsequently, it amalgamates these networks with the Deeplabv3+ head after integrating the convolutional block attention mechanism (CBAM). Notably, this amalgamation harmonizes distinct scale features extracted by the three backbone networks, thus enriching the model’s spatial contextual comprehension and expanding its receptive field, thereby facilitating more effective semantic feature extraction across different stages. The convolutional block attention mechanism primarily orchestrates channel adjustments and curtails redundant information within the aggregated feature layers. Ablation experiments demonstrate an enhancement of no less than 3% in the mean intersection over union (mIoU) of ABNet on both the LoveDA and GID15 datasets when compared with a single backbone network model. Furthermore, in contrast to seven classical or state-of-the-art models (UNet, FPN, PSPNet, DANet, CBNet, CCNet, and UPerNet), ABNet evinces excellent segmentation performance across the aforementioned datasets, underscoring the efficiency and robust generalization capabilities of the proposed approach. Full article
Show Figures

Figure 1

24 pages, 12899 KiB  
Article
Regional Accuracy Assessment of 30-Meter GLC_FCS30, GlobeLand30, and CLCD Products: A Case Study in Xinjiang Area
by Jingpeng Liu, Yu Ren and Xidong Chen
Remote Sens. 2024, 16(1), 82; https://doi.org/10.3390/rs16010082 - 25 Dec 2023
Cited by 5 | Viewed by 1624
Abstract
With the development of remote sensing technology, a number of fine-resolution (30-m) global/national land cover (LC) products have been developed. However, accuracy assessments for the developed LC products are commonly conducted at global and national scales. Due to the limited availability of representative [...] Read more.
With the development of remote sensing technology, a number of fine-resolution (30-m) global/national land cover (LC) products have been developed. However, accuracy assessments for the developed LC products are commonly conducted at global and national scales. Due to the limited availability of representative validation observations and reference data, knowledge relating to the accuracy and applicability of existing LC products on a regional scale is limited. Since Xinjiang, China, exhibits diverse surface cover and fragmented urban landscapes, existing LC products generally have high classification uncertainty in this region. This makes Xinjiang suitable for assessing the accuracy and consistency of exiting fine-resolution land cover products. In order to improve knowledge of the accuracy of existing fine-resolution LC products at the regional scale, Xinjiang province was selected as the case area. First, we employed an equal-area stratified random sampling approach with climate, population density, and landscape heterogeneity information as constraints, along with the hexagonal discrete global grid system (HDGGS) as basic sampling grids to develop a high-density land cover validation dataset for Xinjiang (HDLV-XJ) in 2020. This is the first publicly available regionally high-density validation dataset that can support analysis at a regional scale, comprising a total of 20,932 validation samples. Then, based on the generated HDLV-XJ dataset, the accuracies and consistency among three widely used 30-m LC products, GLC_FCS30, GlobeLand30, and CLCD, were quantitatively evaluated. The results indicated that the CLC_FCS30 exhibited the highest overall accuracy (88.10%) in Xinjiang, followed by GlobeLand30 (with an overall accuracy of 83.58%) and CLCD (81.57%). Moreover, through a comprehensive analysis of the relationship between different environmental conditions and land cover product performance, we found that GlobeLand30 performed best in regions with high landscape fragmentation, while GLC_FCS30 stood out as the most outstanding product in areas with uneven proportions of land cover types. Our study provides a novel insight into the suitability of these three widely-used LC products under various environmental conditions. The findings and dataset can provide valuable insights for the application of existing LC products in different environment conditions, offering insights into their accuracies and limitations. Full article
Show Figures

Figure 1

24 pages, 3925 KiB  
Article
Data-Driven Approaches for Wildfire Mapping and Prediction Assessment Using a Convolutional Neural Network (CNN)
by Rida Kanwal, Warda Rafaqat, Mansoor Iqbal and Song Weiguo
Remote Sens. 2023, 15(21), 5099; https://doi.org/10.3390/rs15215099 - 25 Oct 2023
Cited by 5 | Viewed by 2500
Abstract
As wildfires become increasingly perilous amidst Pakistan’s expanding population and evolving environmental conditions, their global significance necessitates urgent attention and concerted efforts toward proactive measures and international cooperation. This research strives to comprehensively enhance wildfire prediction and management by implementing various measures to [...] Read more.
As wildfires become increasingly perilous amidst Pakistan’s expanding population and evolving environmental conditions, their global significance necessitates urgent attention and concerted efforts toward proactive measures and international cooperation. This research strives to comprehensively enhance wildfire prediction and management by implementing various measures to contribute to proactive mitigation in Pakistan. Additionally, the objective of this research was to acquire an extensive understanding of the factors that influence fire patterns in the country. For this purpose, we looked at the spatiotemporal patterns and causes of wildfires between 2000 and 2023 using descriptive analysis. The data analysis included a discussion on density-based clustering as well as the distribution of the data across four seasons over a period of six years. Factors that could indicate the probability of a fire occurrence such as weather conditions, terrain characteristics, and fuel availability encompass details about the soil, economy, and vegetation. We used a convolutional neural network (CNN) to extract features, and different machine learning (ML) techniques were implemented to obtain the best model for wildfire prediction. The majority of fires in the past six years have primarily occurred during the winter months in coastal locations. The occurrence of fires was accurately predicted by ML models such as random forest (RF), which outperformed competing models. Meanwhile, a CNN with 1D and 2D was used for more improvement in prediction by ML models. The accuracy increased from an 86.48 to 91.34 accuracy score by just using a CNN 1D. For more feature extraction, a CNN 2D was used on the same dataset, which led to state-of-the-art prediction results. A 96.91 accuracy score was achieved by further tuning the RF model on the total data. Data division by spatial and temporal changes was also used for the better prediction of fire, which can further be helpful for understanding the different prospects of wildfire. This research aims to advance wildfire prediction methodologies by leveraging ML techniques to explore the benefits and limitations of capturing complex patterns and relationships in large datasets. Policymakers, environmentalists, and scholars studying climate change can benefit greatly from the study’s analytical approach, which may assist Pakistan in better managing and reducing wildfires. Full article
Show Figures

Graphical abstract

21 pages, 14121 KiB  
Article
Semantic Segmentation of China’s Coastal Wetlands Based on Sentinel-2 and Segformer
by Xufeng Lin, Youwei Cheng, Gong Chen, Wenjing Chen, Rong Chen, Demin Gao, Yinlong Zhang and Yongbo Wu
Remote Sens. 2023, 15(15), 3714; https://doi.org/10.3390/rs15153714 - 25 Jul 2023
Cited by 6 | Viewed by 2354
Abstract
Concerning the ever-changing wetland environment, the efficient extraction of wetland information holds great significance for the research and management of wetland ecosystems. China’s vast coastal wetlands possess rich and diverse geographical features. This study employs the SegFormer model and Sentinel-2 data to conduct [...] Read more.
Concerning the ever-changing wetland environment, the efficient extraction of wetland information holds great significance for the research and management of wetland ecosystems. China’s vast coastal wetlands possess rich and diverse geographical features. This study employs the SegFormer model and Sentinel-2 data to conduct a wetland classification study for coastal wetlands in Yancheng, Jiangsu, China. After preprocessing the Sentinel data, nine classification objects (construction land, Spartina alterniflora (S. alterniflora), Suaeda salsa (S. salsa), Phragmites australis (P. australis), farmland, river system, aquaculture and tidal falt) were identified based on the previous literature and remote sensing images. Moreover, mAcc, mIoU, aAcc, Precision, Recall and F-1 score were chosen as evaluation indicators. This study explores the potential and effectiveness of multiple methods, including data image processing, machine learning and deep learning. The results indicate that SegFormer is the best model for wetland classification, efficiently and accurately extracting small-scale features. With mIoU (0.81), mAcc (0.87), aAcc (0.94), mPrecision (0.901), mRecall (0.876) and mFscore (0.887) higher than other models. In the face of unbalanced wetland categories, combining CrossEntropyLoss and FocalLoss in the loss function can improve several indicators of difficult cases to be segmented, enhancing the classification accuracy and generalization ability of the model. Finally, the category scale pie chart of Yancheng Binhai wetlands was plotted. In conclusion, this study achieves an effective segmentation of Yancheng coastal wetlands based on the semantic segmentation method of deep learning, providing technical support and reference value for subsequent research on wetland values. Full article
Show Figures

Figure 1

19 pages, 4240 KiB  
Article
Paddy Rice Phenological Mapping throughout 30-Years Satellite Images in the Honghe Hani Rice Terraces
by Jianbo Yang, Jianchu Xu, Ying Zhou, Deli Zhai, Huafang Chen, Qian Li and Gaojuan Zhao
Remote Sens. 2023, 15(9), 2398; https://doi.org/10.3390/rs15092398 - 4 May 2023
Cited by 7 | Viewed by 3383
Abstract
The Honghe Hani Rice Terraces represent the coexistence between natural and cultural systems. Despite being listed as a World Heritage Site in 2013, certain natural and anthropogenic factors have changed land use/land cover, which has led to a reduction in the size of [...] Read more.
The Honghe Hani Rice Terraces represent the coexistence between natural and cultural systems. Despite being listed as a World Heritage Site in 2013, certain natural and anthropogenic factors have changed land use/land cover, which has led to a reduction in the size of the paddy rice area. It is difficult to accurately assess these changes due to the lack of historical maps of paddy rice croplands with fine spatial resolution. Therefore, we integrated a random forest classifier and phenological information to improve mapping accuracy and stability. We then mapped the historical distribution of land use/land cover in the Honghe Hani Rice Terraces from 1989–1991 to 2019–2021 using the Google Earth Engine. Finally, we analyzed the driving forces of land use types in the Honghe Hani Rice Terraces. We found that: (1) forests, shrubs or grasslands, and other croplands could be discriminated from paddy rice during the flooding and transplanting period, and water bodies and buildings could also be discriminated from paddy rice during the growing and harvesting period. (2) Inputting phenological feature data improved mapping accuracy and stability compared with single phenological periods. (3) In the past thirty years, 10.651%, 8.810%, and 5.711% of paddy rice were respectively converted to forests, shrubs or grasslands, and other croplands in the Honghe Hani Rice Terraces. (4) Lower agricultural profits and drought led to problems in identifying the driving mechanisms behind paddy rice distribution changes. This study demonstrates that phenological information can improve the mapping accuracy of rice terraces. It also provides evidence for the change in the size of the rice terrace area and associated driving forces in Southwest China. Full article
Show Figures

Figure 1

20 pages, 1110 KiB  
Article
Double Branch Parallel Network for Segmentation of Buildings and Waters in Remote Sensing Images
by Jing Chen, Min Xia, Dehao Wang and Haifeng Lin
Remote Sens. 2023, 15(6), 1536; https://doi.org/10.3390/rs15061536 - 11 Mar 2023
Cited by 41 | Viewed by 3342
Abstract
The segmentation algorithm for buildings and waters is extremely important for the efficient planning and utilization of land resources. The temporal and space range of remote sensing pictures is growing. Due to the generic convolutional neural network’s (CNN) insensitivity to the spatial position [...] Read more.
The segmentation algorithm for buildings and waters is extremely important for the efficient planning and utilization of land resources. The temporal and space range of remote sensing pictures is growing. Due to the generic convolutional neural network’s (CNN) insensitivity to the spatial position information in remote sensing images, certain location and edge details can be lost, leading to a low level of segmentation accuracy. This research suggests a double-branch parallel interactive network to address these issues, fully using the interactivity of global information in a Swin Transformer network, and integrating CNN to capture deeper information. Then, by building a cross-scale multi-level fusion module, the model can combine features gathered using convolutional neural networks with features derived using Swin Transformer, successfully extracting the semantic information of spatial information and context. Then, an up-sampling module for multi-scale fusion is suggested. It employs the output high-level feature information to direct the low-level feature information and recover the high-resolution pixel-level features. According to experimental results, the proposed networks maximizes the benefits of the two models and increases the precision of semantic segmentation of buildings and waters. Full article
Show Figures

Figure 1

25 pages, 7397 KiB  
Article
Scale-Invariant Multi-Level Context Aggregation Network for Weakly Supervised Building Extraction
by Jicheng Wang, Xin Yan, Li Shen, Tian Lan, Xunqiang Gong and Zhilin Li
Remote Sens. 2023, 15(5), 1432; https://doi.org/10.3390/rs15051432 - 3 Mar 2023
Cited by 6 | Viewed by 2213
Abstract
Weakly supervised semantic segmentation (WSSS) methods, utilizing only image-level annotations, are gaining popularity for automated building extraction due to their advantages in eliminating the need for costly and time-consuming pixel-level labeling. Class activation maps (CAMs) are crucial for weakly supervised methods to generate [...] Read more.
Weakly supervised semantic segmentation (WSSS) methods, utilizing only image-level annotations, are gaining popularity for automated building extraction due to their advantages in eliminating the need for costly and time-consuming pixel-level labeling. Class activation maps (CAMs) are crucial for weakly supervised methods to generate pseudo-pixel-level labels for training networks in semantic segmentation. However, CAMs only activate the most discriminative regions, leading to inaccurate and incomplete results. To alleviate this, we propose a scale-invariant multi-level context aggregation network to improve the quality of CAMs in terms of fineness and completeness. The proposed method has integrated two novel modules into a Siamese network: (a) a self-attentive multi-level context aggregation module that generates and attentively aggregates multi-level CAMs to create fine-structured CAMs and (b) a scale-invariant optimization module that cooperates with mutual learning and coarse-to-fine optimization to improve the completeness of CAMs. The results of the experiments on two open building datasets demonstrate that our method achieves new state-of-the-art building extraction results using only image-level labels, producing more complete and accurate CAMs with an IoU of 0.6339 on the WHU dataset and 0.5887 on the Chicago dataset, respectively. Full article
Show Figures

Graphical abstract

24 pages, 17018 KiB  
Article
Impacts of Green Fraction Changes on Surface Temperature and Carbon Emissions: Comparison under Forestation and Urbanization Reshaping Scenarios
by Faisal Mumtaz, Jing Li, Qinhuo Liu, Aqil Tariq, Arfan Arshad, Yadong Dong, Jing Zhao, Barjeece Bashir, Hu Zhang, Chenpeng Gu and Chang Liu
Remote Sens. 2023, 15(3), 859; https://doi.org/10.3390/rs15030859 - 3 Feb 2023
Cited by 21 | Viewed by 4425
Abstract
Global land cover dynamics alter energy, water, and greenhouse gas exchange between land and atmosphere, affecting local to global weather and climate change. Although reforestation can provide localized cooling, ongoing land use land cover (LULC) shifts are expected to exacerbate urban heat island [...] Read more.
Global land cover dynamics alter energy, water, and greenhouse gas exchange between land and atmosphere, affecting local to global weather and climate change. Although reforestation can provide localized cooling, ongoing land use land cover (LULC) shifts are expected to exacerbate urban heat island impacts. In this study, we monitored spatiotemporal changes in green cover in response to land use transformation associated with the Khyber Pakhtunkhwa (KPK) provincial government’s Billion Tree Tsunami Project (BTTP) and the Ravi Urban Development Plan (RUDP) initiated by the provincial government of Punjab, both in Pakistan. The land change modeler (LCM) was used to assess the land cover changes and transformations between 2000 and 2020 across Punjab and KPK. Furthermore, a curve fit linear regression model (CFLRM) and sensitivity analysis were employed to analyze the impacts of land cover dynamics on land surface temperature (LST) and carbon emissions (CE). Results indicated a significant increase in green fraction of +5.35% under the BTTP, achieved by utilizing the bare land with an effective transition of 4375.87 km2. However, across the Punjab province, an alarming reduction in green fraction cover by −1.77% and increase in artificial surfaces by +1.26% was noted. A significant decrease in mean monthly LST by −4.3 °C was noted in response to the BTTP policy, while an increase of 5.3 °C was observed associated with the RUDP. A substantial increase in LST by 0.17 °C was observed associated with transformation of vegetation to artificial surfaces. An effective decrease in LST by −0.21 °C was observed over the opposite transition. Furthermore, sensitivity analysis suggested that LST fluctuations are affecting the % of CO2 emission. The current findings can assist policymakers in revisiting their policies to promote ecological conservation and sustainability in urban planning. Full article
Show Figures

Figure 1

21 pages, 13734 KiB  
Article
Active Pairwise Constraint Learning in Constrained Time-Series Clustering for Crop Mapping from Airborne SAR Imagery
by Xingli Qin, Lingli Zhao, Jie Yang, Pingxiang Li, Bingfang Wu, Kaimin Sun and Yubin Xu
Remote Sens. 2022, 14(23), 6073; https://doi.org/10.3390/rs14236073 - 30 Nov 2022
Cited by 1 | Viewed by 1530
Abstract
Airborne SAR is an important data source for crop mapping and has important applications in agricultural monitoring and food safety. However, the incidence-angle effects of airborne SAR imagery decrease the crop mapping accuracy. An active pairwise constraint learning method (APCL) is proposed for [...] Read more.
Airborne SAR is an important data source for crop mapping and has important applications in agricultural monitoring and food safety. However, the incidence-angle effects of airborne SAR imagery decrease the crop mapping accuracy. An active pairwise constraint learning method (APCL) is proposed for constrained time-series clustering to address this problem. APCL constructs two types of instance-level pairwise constraints based on the incidence angles of the samples and a non-iterative batch-mode active selection scheme: the must-link constraint, which links two objects of the same crop type with large differences in backscattering coefficients and the shapes of time-series curves; the cannot-link constraint, which links two objects of different crop types with only small differences in the values of backscattering coefficients. Experiments were conducted using 12 time-series images with incidence angles ranging from 21.2° to 64.3°, and the experimental results prove the effectiveness of APCL in improving crop mapping accuracy. More specifically, when using dynamic time warping (DTW) as the similarity measure, the kappa coefficient obtained by APCL was increased by 9.5%, 8.7%, and 5.2% compared to the results of the three other methods. It provides a new solution for reducing the incidence-angle effects in the crop mapping of airborne SAR time-series images. Full article
Show Figures

Graphical abstract

23 pages, 9722 KiB  
Article
Convolutional Neural Networks for Agricultural Land Use Classification from Sentinel-2 Image Time Series
by Alejandro-Martín Simón Sánchez, José González-Piqueras, Luis de la Ossa and Alfonso Calera
Remote Sens. 2022, 14(21), 5373; https://doi.org/10.3390/rs14215373 - 27 Oct 2022
Cited by 20 | Viewed by 3985
Abstract
Land use classification (LUC) is the process of providing information on land cover and the types of human activity involved in land use. In this study, we perform agricultural LUC using sequences of multispectral reflectance Sentinel-2 images taken in 2018. LUC can be [...] Read more.
Land use classification (LUC) is the process of providing information on land cover and the types of human activity involved in land use. In this study, we perform agricultural LUC using sequences of multispectral reflectance Sentinel-2 images taken in 2018. LUC can be carried out using machine or deep learning techniques. Some existing models process data at the pixel level, performing LUC successfully with a reduced number of images. Part of the pixel information corresponds to multispectral temporal patterns that, despite not being especially complex, might remain undetected by models such as random forests or multilayer perceptrons. Thus, we propose to arrange pixel information as 2D yearly fingerprints so as to render such patterns explicit and make use of a CNN to model and capture them. The results show that our proposal reaches a 91% weighted accuracy in classifying pixels among 19 classes, outperforming random forest by 8%, or a specifically tuned multilayer perceptron by 4%. Furthermore, models were also used to perform a ternary classification in order to detect irrigated fields, reaching a 97% global accuracy. We can conclude that this is a promising operational tool for monitoring crops and water use over large areas. Full article
Show Figures

Figure 1

Back to TopTop