Land use and land cover classification with hyperspectral data: A comprehensive review of methods, challenges and future directions

Moharram, Mohammed Abdulmajeed; Sundaram, Divya Meena

doi:10.1016/j.neucom.2023.03.025

Cited by 60 publications

(11 citation statements)

References 166 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main performance metrics commonly used to evaluate LULC classification models are overall accuracy (OA), average accuracy (AA), F1-score (F1), and mean intersection and parallel ratio (MIOU) [46].…”

Section: Performance Indicatorsmentioning

confidence: 99%

Land Use and Land Cover Classification Meets Deep Learning: A Review

Zhao,

Tu,

et al. 2023

Sensors

View full text Add to dashboard Cite

As one of the important components of Earth observation technology, land use and land cover (LULC) image classification plays an essential role. It uses remote sensing techniques to classify specific categories of ground cover as a means of analyzing and understanding the natural attributes of the Earth’s surface and the state of land use. It provides important information for applications in environmental protection, urban planning, and land resource management. However, remote sensing images are usually high-dimensional data and have limited available labeled samples, so performing the LULC classification task faces great challenges. In recent years, due to the emergence of deep learning technology, remote sensing data processing methods based on deep learning have achieved remarkable results, bringing new possibilities for the research and development of LULC classification. In this paper, we present a systematic review of deep-learning-based LULC classification, mainly covering the following five aspects: (1) introduction of the main components of five typical deep learning networks, how they work, and their unique benefits; (2) summary of two baseline datasets for LULC classification (pixel-level, patch-level) and performance metrics for evaluating different models (OA, AA, F1, and MIOU); (3) review of deep learning strategies in LULC classification studies, including convolutional neural networks (CNNs), autoencoders (AEs), generative adversarial networks (GANs), and recurrent neural networks (RNNs); (4) challenges faced by LULC classification and processing schemes under limited training samples; (5) outlooks on the future development of deep-learning-based LULC classification.

show abstract

Section: Performance Indicatorsmentioning

confidence: 99%

Land Use and Land Cover Classification Meets Deep Learning: A Review

Zhao,

Tu,

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…This also showed that human activities are an important driving force for short-term regional landscape changes (Li et al, 2019). In recent years, with policy support for poverty alleviation and development and rural revitalization, China's land use in desert areas has shown new characteristics of change (Liu et al, 2014) and has changed from "sand advancing and people retreating" (Moharram and Sundaram, 2023) into a new situation of "harmony between man and sand" (Parker-Shames et al, 2023).…”

Section: Discussionmentioning

confidence: 96%

Changes in land use and ecosystem service value in desert areas of China after reform and opening up

Ba,

Du,

Hasi

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

Desert areas of China have important ecological functions, so analyzing changing characteristics of ecosystem service values in this region is important for sustainable development. Using land use change data for desert areas from 1978 to 2022, this paper combined the equivalent factor method and the actual situation of the study area to revise value coefficients of ecosystem services and study characteristics of land use and ecosystem service value changes after reform and opening up. The results showed that after reform and opening up, the area of plow, water, and other lands in the study area decreased, while grassland, forest, construction land, and sandy land increased. The conversion of a land use type mainly occurred as conversion of grassland and other lands to other land use types. The value of ecosystem services increased, increasing by 19.63 × 108 CNY. From the perspective of land use type in 2022, the ecosystem service value of grassland was the highest, reaching 12.19 × 108 CNY, an increase of 11.73 × 108 CNY compared with the early stage of reform and opening up. From the perspective of ecosystem service types in 2022, the value of maintaining soil ecological services was the highest, reaching 3.07 × 108 CNY, an increase of 2.97 × 108 CNY compared with the beginning of reform and opening up. From the perspective of the ecological sensitivity index, the sensitivity index results for the ecosystem service value in the study area were all <1, and the research results were credible. From the perspective of the land ecological coordination degree, the overall land ecological coordination degree in the study area was at a moderate coordination level, indicating that land use change did not lead to environmental deterioration, but there was a crisis. Therefore, increasing and maintaining ecological land is the key to improving ESV in the study area.

show abstract

“…This invisible state, alongside input vectors, undergoes updates and subsequently serves as an output alongside output vectors (Stateczny et al, 2022). Notably, the updated hidden state becomes part of the following input, preserving prior information (Moharram and Sundaram, 2023). RNNs find application in Land Use and Land Cover (LULC) classification in remote sensing images, which often encompass temporal and spatial data due to their robust material processing capabilities (Zhao et al, 2023).…”

Section: Recurrent Neural Network (Rnn)mentioning

confidence: 99%

Comparison of machine and deep learning algorithms using Google Earth Engine and Python for land classifications

Nigar,

Li,

Jat Baloch

et al. 2024

Front. Environ. Sci.

View full text Add to dashboard Cite

Classifying land use and land cover (LULC) is essential for various environmental monitoring and geospatial analysis applications. This research focuses on land classification in District Sukkur, Pakistan, employing the comparison between machine and deep learning models. Three satellite indices, namely, NDVI, MNDWI, and NDBI, were derived from Landsat-8 data and utilized to classify four primary categories: Built-up Area, Water Bodies, Barren Land, and Vegetation. The main objective of this study is to evaluate and compare the effectiveness of comparison of machine and deep learning models. The machine learning models including Random Forest achieved an overall accuracy of 91.3% and a Kappa coefficient of 0.90. It accurately classified 2.7% of the area as Built-up Area, 1.9% as Water Bodies, 54.8% as Barren Land, and 40.4% as Vegetation. While slightly less accurate, Decision Tree model provided reliable classifications. Deep learning models showed significant accuracy, of Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). The CNN model achieved an impressive overall accuracy of 97.3%, excelling in classifying Water Bodies with User and Producer Accuracy exceeding 99%. The RNN model, with an overall accuracy of 96.2%, demonstrated strong performance in categorizing Vegetation. These findings offer valuable insights into the potential applications of machine learning and deep learning models for perfect land classifications, with implications for environmental monitoring management and geospatial analysis. The rigorous validation and comparative analysis of these models contribute to advancing remote sensing techniques and their utilization in land classification tasks. This research presents a significant contribution to the field and underscores the importance of precise land classification in the context of sustainable land management and environmental conservation.

show abstract

Land use and land cover classification with hyperspectral data: A comprehensive review of methods, challenges and future directions

Cited by 60 publications

References 166 publications

Land Use and Land Cover Classification Meets Deep Learning: A Review

Land Use and Land Cover Classification Meets Deep Learning: A Review

Changes in land use and ecosystem service value in desert areas of China after reform and opening up

Comparison of machine and deep learning algorithms using Google Earth Engine and Python for land classifications

Contact Info

Product

Resources

About