Land Use And Land Cover Classes Research Articles

Spatiotemporal trends of urban-induced land use and land cover change and implications on catchment surface imperviousness

Urbanization, changes in land use and land cover (LULC), and an increase in population collectively have significant impacts on urban catchments. However, a vast majority of LULC studies have been conducted using readily available satellite imagery, which often presents limitations due to its coarse spatial resolution. Such imagery fails to accurately depict the surface characteristics and diverse spectrum of LULC classifications contained within a single pixel. This study focused on the highly urbanized Dry Creek catchment in Adelaide, South Australia and aimed to determine the impact of urbanization on spatiotemporal changes in LULC and its implications for the land surface condition of the catchment. Very high spatial resolution imagery was utilized to examine changes in LULC over the past four decades. Support Vector Machine-learning-based image classification was utilized to classify and identify the changes in LULC over the study area. The classification accuracy showed strong agreement, with a kappa value greater than 0.8. The findings of this analysis showed that extensive urban development, which expanded the built-up area by 34 km2, were responsible for the decline in grass cover by 43.1 km2 over the last 40 years (1979–2019). Moreover, built-up areas, plantation, and water features, in contrast to grass cover, have demonstrated an increasing trend during the study period. The overall urban expansion over the study period was 136.6%. Urbanization intensified impervious area coverage, increasing the runoff coefficient, equivalent impervious area, and curve number by 60.6%, 60.6%, and 7.9%, respectively, while decreasing the retention capacity by 38.6%. These modifications suggest a potential variability in catchment surface runoff, prompting the need for further research to understand the surface runoff changes brought by the changes in LULC resulting from urbanization. The findings of this study can be used for land use planning and flood management.

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

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.

Analytical study of relation between Land surface temperature and Land Use/Land Cover using spectral indices: A case study of Chandigarh

Rapid urbanization is the major cause for Land Use and Land Cover changes globally. The urbanization alters the land surface dynamics and affects the surface temperature, which gives rise to urban heat island effect. In the present study, spatial correlation analysis has been done between Land Surface Temperature (LST) and Land Use and Land Cover (LULC) for the city of Chandigarh. The LST is retrieved from Landsat-8 thermal band using Mono-Window algorithm and shows 2.5°C increase of temperature from 2016 to 2022. The LULC has been derived using Maximum Likelihood Classifier (MLC) which shows an increase in built-up of 7.56% and decrease in forest cover by 32%. Spectral indices belonging to major LULC classes have been derived using Sentinel-2 optical bands and spatially correlated with LST using linear regression analysis. The results show a strong positive correlation (r=0.988) between built-up and LST and a negative correlation (r=-0.625) between urban vegetation cover and LST. The mean correlation coefficient for LST-NDVI for vegetation and forest cover, LST-NDWI for water bodies, LST-NDBI for built-up and LST-NBLI for bare land is -0.3, 0.116, 0.51 and 0.392 respectively. The results indicate that vegetation and water bodies mitigate the rise of LST, whereas built-up areas and bare lands sustain in the rise of LST. The statistical analysis will be helpful for policy makers and urban planners for prevention of further degradation of urban environment and surface dynamics.

Land Use and Land Cover Change Modulates Hydrological Flows and Water Supply to Gaborone Dam Catchment, Botswana

Identifying the mechanism through which changes in land use and land cover (LULC) modulate hydrological flows is vital for water resource planning and management. To examine the impact of LULC change on the hydrology of the Gaborone Dam catchment within the upper Limpopo basin, where Notwane river is the major river within the catchment, three LULC maps for the years 1997, 2008, and 2017 were established based on a mosaic of Landsat 5 for 1997 and 2008 and Landsat 8 for 2017. The 10 m-resolution Version 200 ESA World Land Cover Map for 2021 is used as a ground truth to train the random forest (RF) classifier to identify land cover classes from Landsat 8 imageries of 2021 using the Google Earth Engine (GEE) Python API. The overall accuracy/kappa coefficient of the RF classifier is 0.99/0.99 for the training and 0.73/0.68 for the validation data sets, which indicate excellent and substantial agreements with the ground truth, respectively. With this confidence in the LULC classification, the impact of LULC change on the hydrological flow within the catchment was estimated by employing the Soil and Water Assessment Tool (SWAT) and indicator of hydrological alteration (IHA). The SWAT model calibration and validation were first performed, and the ability of the model to capture the observed stream flow was found to be good. The LULC maps from Landsat images during the 1997–2017 period show a decrease in forests and shrubland in contrast to an increase in pasture land. The expansion of pasture and cropland and the reduction in forests and shrubland led to a decline in the amount of evapotranspiration and groundwater recharge. Furthermore, the LULC change also caused a reduction in low flow during dry periods and an increase in high flow during the rainy season. The findings clearly demonstrate that LULC changes can affect the water table by altering soil water recharge capacity. The study highlighted the importance of LULC for catchment water resource management through land use planning to regulate the water level in the Gaborone Dam against the impact of climate change and growing water demands by the city of Gaborone due to population growth.

Toward understanding land use land cover changes and their effects on land surface temperature in yam production area, Côte d'Ivoire, Gontougo Region, using remote sensing and machine learning tools (Google Earth Engine)

Land use and land cover (LULC) changes are one of the main factors contributing to ecosystem degradation and global climate change. This study used the Gontougo Region as a study area, which is fast changing in land occupation and most vulnerable to climate change. The machine learning (ML) method through Google Earth Engine (GEE) is a widely used technique for the spatiotemporal evaluation of LULC changes and their effects on land surface temperature (LST). Using Landsat 8 OLI and TIRS images from 2015 to 2022, we analyzed vegetation cover using the Normalized Difference Vegetation Index (NDVI) and computed LST. Their correlation was significant, and the Pearson correlation (r) was negative for each correlation over the year. The correspondence of the NDVI and LST reclassifications has also shown that non-vegetation land corresponds to very high temperatures (34.33°C–45.22°C in 2015 and 34.26°C–45.81°C in 2022) and that high vegetation land corresponds to low temperatures (17.33°C–28.77°C in 2015 and 16.53 29.11°C in 2022). Moreover, using a random forest algorithm (RFA) and Sentinel-2 images for 2015 and 2022, we obtained six LULC classes: bareland and settlement, forest, waterbody, savannah, annual crops, and perennial crops. The overall accuracy (OA) of each LULC map was 93.77% and 96.01%, respectively. Similarly, the kappa was 0.87 in 2015 and 0.92 in 2022. The LULC classes forest and annual crops lost 48.13% and 65.14%, respectively, of their areas for the benefit of perennial crops from 2015 to 2022. The correlation between LULC and LST showed that the forest class registered the low mean temperature (28.69°C in 2015 and 28.46°C in 2022), and the bareland/settlement registered the highest mean temperature (35.18°C in 2015 and 35.41°C in 2022). The results show that high-resolution images can be used for monitoring biophysical parameters in vegetation and surface temperature and showed benefits for evaluating food security.

Using Landsat-5 for Accurate Historical LULC Classification: A Comparison of Machine Learning Models

This study investigates the application of various machine learning models for land use and land cover (LULC) classification in the Kerch Peninsula. The study utilizes archival field data, cadastral data, and published scientific literature for model training and testing, using Landsat-5 imagery from 1990 as input data. Four machine learning models (deep neural network, Random Forest, support vector machine (SVM), and AdaBoost) are employed, and their hyperparameters are tuned using random search and grid search. Model performance is evaluated through cross-validation and confusion matrices. The deep neural network achieves the highest accuracy (96.2%) and performs well in classifying water, urban lands, open soils, and high vegetation. However, it faces challenges in classifying grasslands, bare lands, and agricultural areas. The Random Forest model achieves an accuracy of 90.5% but struggles with differentiating high vegetation from agricultural lands. The SVM model achieves an accuracy of 86.1%, while the AdaBoost model performs the lowest with an accuracy of 58.4%. The novel contributions of this study include the comparison and evaluation of multiple machine learning models for land use classification in the Kerch Peninsula. The deep neural network and Random Forest models outperform SVM and AdaBoost in terms of accuracy. However, the use of limited data sources such as cadastral data and scientific articles may introduce limitations and potential errors. Future research should consider incorporating field studies and additional data sources for improved accuracy. This study provides valuable insights for land use classification, facilitating the assessment and management of natural resources in the Kerch Peninsula. The findings contribute to informed decision-making processes and lay the groundwork for further research in the field.

Dynamics of the wetland ecosystem health in urban and rural settings in high altitude ecoregion

The focus of the present study was to assess the dynamics of wetland ecosystem health in both urban and rural settings situated in the high-altitude Kashmir Himalayan ecoregion. The basic aim was to identify the drivers responsible for wetland degradation in order to sustain ecosystem services effectively. To achieve this, we examined water quality, trophic status, fish species diversity and human disturbances by analyzing changes in land use and land cover (LULC) since 1980. For the limnological characterization of the two wetlands, we evaluated a total of 21 physico-chemical parameters at 24 sites. Two-way analysis of variance revealed significant (p < 0.05) spatial and temporal variability in the water quality parameters. The trophic state index values of 67.7 and 76.7 indicated that the rural and urban wetlands were in eutrophic and hypertrophic status, respectively, signifying potential environmental stress. The data on fish fauna indicated a decline in fish species over the past 40 years, particularly the schizothoracine species. Urban wetlands showed a more significant decrease in species (06) compared to rural wetlands (01). LULC mapping and change analysis employing the visual interpretation technique showed significant transformations in the immediate catchment of wetlands. Substantial growth in the built-up (433.2 % and 2620 %) and decrease in aquatic vegetation (−83.4 % and − 97.5 %) in the immediate catchment was recorded in both the urban and rural wetlands respectively from 1980 to 2020. Our findings demonstrated a relationship between LULC classes and water quality parameters, with an increase in built-up and road areas showing a significant positive correlation with the rise in decadal mean values of total phosphorus, orthophosphorus, nitrate nitrogen, ammonical nitrogen, and calcium content. Based on these observations, we concluded that changes in land use and land cover within the immediate catchment areas of the wetlands were the primary drivers responsible for the deterioration of wetland ecosystem health.

The Land-Use and Land-Cover Changes in the Este District, South Gondar Zone, Northwestern Ethiopia, in the Last Four Decades (the 1980s to 2020s)

Environmental transformations are the results of land-use and land-cover (LULC) changes. This study aims to investigate the LULC changes and associated factors in the Este District in northwestern Ethiopia, for the last four decades (the 1980s to 2020s). The land-use and land-cover classes were analyzed using supervised classification techniques in ERDASS IMAGINE 2015 and ArcGIS 10.3.1, categorizing the Landsat satellite images for 1984, 2000, and 2018 into six cover classes: settlement, forests-shrublands, cropland, grassland, bare land, and water body. We used a historical Google map, topo-sheets, and ancillary data to verify the classification accuracies for 1984, 2000, and 2018, respectively. The climate and demographic data were obtained from the Ethiopian Meteorological Station and Ethiopian Statistical Agency, respectively. In addition, data from key informant interviews and focus group discussions were also used to understand the local community experiences and perceptions toward LULC changes. The values of each LULC class were correlated with the demographic and climatic variables, using simple correlation analysis to evaluate the impact of demographic and climatic conditions on LULC changes. The analysis indicated that the least and largest classes of LULC in Este District were water bodies (mean cover = 1.9 km2) and croplands (mean cover = 791.7 km2), respectively. Cropland coverage increased by 2% in 2000, then decreased by 11% in 2018. Between 1984 and 2018, the grasslands and settlements increased by 22% and 0.5%, respectively. Half of the bare land and one-tenth of the forests-shrublands also decreased over the last four decades (the 1980s to 2020s). As a result, the original croplands and forests–shrublands classes (11% each) before 2000 were converted into new grasslands and croplands after 2018, respectively. The study indicated that precipitation, solar radiation, and population growth are the potential drivers, and the perceptions of local communities are nearly in line with the statistical analysis results. Alternative income sources, such as tourism and carbon trading and the participation in afforestation programs, could reverse the situation in the study area.

Mapping Land Use and Land Cover Classes in São Paulo State, Southeast of Brazil, Using Landsat-8 OLI Multispectral Data and the Derived Spectral Indices and Fraction Images

This work aims to develop a new method to map Land Use and Land Cover (LULC) classes in the São Paulo State, Brazil, using Landsat-8 Operational Land Imager (OLI) data. The novelty of the proposed method consists of selecting the images based on the spectral and temporal characteristics of the LULC classes. First, we defined the six classes to be mapped in the year 2020 as forest, forest plantation, water bodies, urban areas, agriculture, and pasture. Second, we visually analyzed their variability spectral characteristics over the year. Then, we pre-processed these images to highlight each LULC class. For the classification, the Random Forest algorithm available on the Google Earth Engine (GEE) platform was utilized individually for each LULC class. Afterward, we integrated the classified maps to create the final LULC map. The results revealed that forest areas are primarily concentrated in the eastern region of São Paulo, predominantly on steeper slopes, accounting for 19% of the study area. On the other hand, pasture and agriculture dominated 73% of all São Paulo’s landscape, reaching 39% and 34%, respectively. The overall accuracy of the classification achieved 89.10%, while producer and user accuracies were greater than 84.20% and 76.62%, respectively. To validate the results, we compared our findings with the MapBiomas Project classification, obtaining an overall accuracy of 85.47%. Therefore, our method demonstrates its potential to minimize classification errors and offers the advantage of facilitating post-classification editing for individual mapped classes.

Land Use and Land Cover Classification in the Northern Region of Mozambique Based on Landsat Time Series and Machine Learning

Accurate land use and land cover (LULC) mapping is essential for scientific and decision-making purposes. The objective of this paper was to map LULC classes in the northern region of Mozambique between 2011 and 2020 based on Landsat time series processed by the Random Forest classifier in the Google Earth Engine platform. The feature selection method was used to reduce redundant data. The final maps comprised five LULC classes (non-vegetated areas, built-up areas, croplands, open evergreen and deciduous forests, and dense vegetation) with an overall accuracy ranging from 80.5% to 88.7%. LULC change detection between 2011 and 2020 revealed that non-vegetated areas had increased by 0.7%, built-up by 2.0%, and dense vegetation by 1.3%. On the other hand, open evergreen and deciduous forests had decreased by 4.1% and croplands by 0.01%. The approach used in this paper improves the current systematic mapping approach in Mozambique by minimizing the methodological gaps and reducing the temporal amplitude, thus supporting regional territorial development policies.

Improving the Accuracy of Land Use and Land Cover Classification of Landsat Data in an Agricultural Watershed

Classification of remotely sensed imagery for reliable land use and land cover (LULC) remains a challenge in areas where spectrally similar LULC features occur. For example, bare soils of harvested crop fields in agricultural watersheds exhibit spectral characteristics similar to high-intensity developed regions and impede an accurate classification. The goal of this study is to improve the accuracy of LULC classification of satellite imagery for the Big Sunflower River Watershed, Mississippi using ancillary data, multiple classification methods, and a post-classification correction (PCC). To determine the best approach, the methodology was applied to Landsat 8 Operational Land Imager (OLI) imagery during the growing season and post-harvest. Imagery for the growing season was acquired on 25 August 2015, and post-harvest was acquired on 7 January 2018. Three classification methods were applied: maximum likelihood (ML), support vector machine (SVM), and random forest (RF). LULC imagery was classified as open water, woody wetlands, harvested crop, rangeland, cultivated crop, high-intensity developed, and mid-low intensity developed areas. Ancillary data such as normalized difference vegetation index (NDVI), thematic maps of urban areas, river networks, transportation networks, high-resolution National Agriculture Imagery Program (NAIP) imagery, Google Earth time-series data, and phenology were used to determine the training dataset. Initially none of the three classification methods performed adequately. Hence, a post-classification correction (PCC) was implemented by masking and applying a majority filter using thematic maps of urban areas. Once PCC was implemented, the accuracies from each of the classification methods increased significantly with the SVM classification method performing best in both the growing season and post-harvest with an overall classification accuracy of 93.5% with a Kappa statistic of 0.88 in the post-harvest imagery and an overall classification accuracy of 84% with a Kappa statistic of 0.789 in the imagery from the growing season. It was found that SVM was the best classification method while PCC is an effective strategy to implement when dealing with spectrally similar LULC features. The use of SVM together with PCC increased the reliability of the information extracted. Strategies from this study can help to evaluate the LULC in agricultural and other watersheds.

Assessment of Object-Based Classification for Mapping Land Use and Land Cover using Google Earth

&lt;p&gt;Land Use and Land Cover (LULC) maps perform a significant part in Remote Sensing (RS) in monitoring and analyzing earth information for human development. Because of the high spectrum variability, LULC classification from RS data is extremely difficult. The study's objective is to assess the object-based LULC classification (OBC) accuracy of composite images from the Landsat 8 OLI (Operational Land Imager) and auxiliary features using SNIC segmentation and five classifiers on Google Earth Engine (GEE). The outcome of the study indicates that the OBC with only spectral features achieves lesser accuracy because small objects on the land surface cannot be observed. But when OBC is paired with a variety of auxiliary features, the OBC may recognize small objects with greater accuracy. After many subsequent assessments the combination of the following aspect: composite image of all the seven bands, new feature set, Simple Non-Iterative Clustering (SNIC) segmentation algorithm, and Support Vector Machine (SVM) classification algorithm gives better accuracy of ~ 94.42% and kappa coefficient of 92.07. The inclusion of auxiliary features and the OBC method reduces the misclassification rate related to the confusion of bare land, uncultivated land, and urban, which provides accurate information on forest, waterbody, and bare land classes.&lt;/p&gt;&#x0D;

Land Use and Land Cover (LULC) Assessment within the Batanes Protected Landscapes and Seascapes

Declared protected areas have ecologically important landscapes that must be conserved and protected. Status of protected areas could be monitored through land use and land cover (LULC) assessments. LULC offers baseline data for integrated land use planning and improvement of existing policies are therefore necessary to be conducted. This study was conducted to monitor the existing LULC of six islands within the Batanes Protected Landscapes and Seascapes (BPLS) through a machine learning (ML)-based random forest (RF) classifier using multi-sourced data such as Landsat imageries’ surface reflectance (SR), Landsat-derived land surface temperature (LST), and global ecosystem dynamic investigation (GEDI)-derived height (Ht) metrics and to determine the effects of the LST and Ht metrics to LULC classification. Four layer stacked images with different features were analyzed – including SR, SR-LST, SR-Ht, and SR-LST-Ht. The result of the LULC classification showed an accuracy based on Macro F1-score and Kappa (K) of 0.81 and 0.83, 0.83and 0.86, 0.86 and 0.89, and 0.93 and 0.94, for SR, SR-LST, SR-Ht, and SR-LST-Ht, respectively. When compared to the existing global-scale LULC, this study has higher accuracy than the GLAD and ESRI products, which have Macro F1-scores and K-values of 0.73 and 0.71, and 0.59 and 0.64, respectively. To conclude, the inclusion of LST and Ht information in addition to SR data in LULC classification can improve the accuracy by up to 12% and 11% based on Macro F1-score and K,respectively. The result of this study can serve as a reference for achieving improved and reliable LULC information that is necessary for monitoring fluctuations of the global earth’s resources and comprehensive LULC planning. In addition, the technique used in this study can serve as a reference in generating reliable LULC information that can aid in the sustainable implementation of policies, rules, and regulations intended for declared protected areas like BPLS.

Vejetasyon İndeksleri, Ana Bileşenler Analizi ve Google Earth Engine Kullanılarak Tarımsal Alan Sınıflandırması: Söke/Aydın Örneği

Land use and land cover (LULC) classification is known to be one of the most widely used indicators of environmental change and degradation all over the world. There are various algorithms and methods for LULC classification, whereby reliability of the classification maps presents the principal concern. The study focused on evaluation of accuracies of LULC maps produced from original bands of Sentinel-2 imageries together with Normalized Difference Vegetation Index (NDVI), Green NDVI (GNDVI), and Principal Component Analysis (PCA) using Google Earth Engine (GEE) platform to identify best enhancing method for agricultural land classification. Moreover, short-term LULC changes aimed to be identified in the specified area. To achieve the aims, all available imageries acquired in the same month of different years with less than 10% cloud contamination were used to compose averaged images for May 2018 and May 2022 for generating LULC2018 and LULC2022 maps. The area has separated into seven main classes, namely, olive (O), perennial cultivation (P), non-perennial cultivation (NP), forest (F), natural vegetation (N), settled area-bare land (S), and water surface (W) via random forest algorithym. Reliabilities of LULC maps were evaluated through accuracy assessment procedures considering stratified randomized control points. Transitions between each LULC classes were identified.

Assessment and Spatial Analysis of Land Use and Land Cover (LULC) Dynamics in the Black Volta Basin

The Black Volta Basin, a critical hydrological region, is experiencing rapid changes in Land Use and Land Cover (LULC) patterns due to diverse anthropogenic and environmental factors. This study employs a comprehensive Multi-Sensor Remote Sensing and Geographic Information System (GIS) methodology to assess and analyze the spatiotemporal dynamics of LULC in the basin. Utilizing data from multiple remote sensing platforms, including optical and radar sensors, as well as historical GIS datasets, a detailed LULC classification is performed. The integration of multi-temporal satellite imagery enables the detection and quantification of changes across distinct land cover categories. Through rigorous spatial analysis and statistical techniques, the study reveals the extent and magnitude of LULC transformations over a defined period. Land cover transitions are identified, characterized, and linked to potential drivers such as urbanization, agricultural expansion, and natural processes. The outcomes of this research contribute to an enhanced understanding of the evolving LULC dynamics in the Black Volta Basin, shedding light on both natural and human-induced changes. The results underscore the significance of a multi-sensor approach in accurately capturing complex LULC changes and their implications for regional sustainability and resource management. This study's insights serve as valuable inputs for policymakers, researchers, and stakeholders engaged in land-use planning, environmental conservation, and sustainable development within the Black Volta Basin and similar ecologically sensitive areas.

Pre-Processing Training Data Improves Accuracy and Generalisability of Convolutional Neural Network Based Landscape Semantic Segmentation

Data pre-processing for developing a generalised land use and land cover (LULC) deep learning model using earth observation data is important for the classification of a different date and/or sensor. However, it is unclear how to approach deep learning segmentation problems in earth observation data. In this paper, we trialled different methods of data preparation for Convolutional Neural Network (CNN) training and semantic segmentation of LULC features within aerial photography over the Wet Tropics and Atherton Tablelands, Queensland, Australia. This was conducted by trialling and ranking various training patch selection sampling strategies, patch and batch sizes, data augmentations and scaling and inference strategies. Our results showed: a stratified random sampling approach for producing training patches counteracted class imbalances; a smaller number of larger patches (small batch size) improves model accuracy; data augmentations and scaling are imperative in creating a generalised model able to accurately classify LULC features in imagery from a different date and sensor; and producing the output classification by averaging multiple grids of patches and three rotated versions of each patch produced a more accurate and aesthetic result. Combining the findings from the trials, we fully trained five models on the 2018 training image and applied the model to the 2015 test image. The output LULC classifications achieved an average kappa of 0.84, user accuracy of 0.81, and producer accuracy of 0.87. Future research using CNNs and earth observation data should implement the findings of this project to increase LULC model accuracy and transferability.

Quantifying the agreement and accuracy characteristics of four satellite-based LULC products for cropland classification in China

Various land use and land cover (LULC) products have been produced over the past decade with the development of remote sensing technology. Despite the differences in LULC classification schemes, there is a lack of research on assessing the accuracy of their application to croplands in a unified framework. Thus, this study evaluated the spatial and area accuracies of cropland classification for four commonly used global LULC products (i.e., MCD12Q1 V6, GlobCover2009, FROM-GLC and GlobeLand30) based on the harmonised FAO criterion, and quantified the relationships between four factors (i.e., slope, elevation, field size and crop system) and cropland classification agreement. The validation results indicated that MCD12Q1 and GlobeLand30 performed well in cropland classification regarding spatial consistency, with overall accuracies of 94.90 and 93.52%, respectively. The FROM-GLC showed the worst performance, with an overall accuracy of 83.17%. Overlaying the cropland generated by the four global LULC products, we found the proportions of complete agreement and disagreement were 15.51 and 44.72% for the cropland classification, respectively. High consistency was mainly observed in the Northeast China Plain, the Huang-Huai-Hai Plain and the northern part of the Middle-lower Yangtze Plain, China. In contrast, low consistency was detected primarily on the eastern edge of the northern and semiarid region, the Yunnan-Guizhou Plateau and southern China. Field size was the most important factor for mapping cropland. For area accuracy, compared with China Statistical Yearbook data at the provincial scale, the accuracies of different products in descending order were: GlobeLand30, FROM-GLC, MCD12Q1, and GlobCover2009. The cropland classification schemes mainly caused large area deviations among the four products, and they also resulted in the different ranks of spatial accuracy and area accuracy among the four products. Our results can provide valuable suggestions for selecting cropland products at the national or provincial scale and help cropland mapping and reconstruction, which is essential for food security and crop management, so they can also contribute to achieving the Sustainable Development Goals issued by the United Nations.

Performance comparison of CNNs on high-resolution multispectral dataset applied to land cover classification problem

Multispectral images acquired by satellites have been used in many fields such as agriculture, urban change detection, finding fire-hazardous forest areas, and real-time surface monitoring. The central issue in remote sensing analysis is land use and land cover classification. Land use and land cover classification (LULC) is the process of classification into meaningful classes based on the spectral characteristics of remote sensing data. Land use and land cover classification is a challenging task due to the complex nature of the Earth's surface. The accuracy of solving the issue using deep learning approaches depends on the quality of the remote sensing data, the choice of the classification algorithm. The ability to obtain high-resolution multispectral images periodically could dramatically improve remote sensing solutions. In this study, we propose a solution for the land cover and land classification problem of high-resolution remote sensing data by applying deep learning methods using EuroPlanet geo-referenced high-quality images with four bands and pixel resolution of 204x204 per image, and acquired by Planet platform in 2020-2022 years. The dataset consists of 25911 images with spatial resolution up to 3.125 meters per pixel and 10 different classes. In the past decade, artificial neural networks have shown great performance in solving complex image classification tasks. For the dataset evaluation, we have taken advantage of state-of-art pretrained convolutional neural network models ResNet50v2, EfficientNetV2, Xception, VGG-16, and DenseNet201 with fine tuning. It has been established that DenseNet201 pretrained neural network outperformed other models. The accuracy of the test data was 92.01 % and the F1 metric was 91.63 %. In addition, bands evaluation for the dataset was carried out. Overall classification accuracy of 93.83 % and F1 score of 93.56 % were achieved by DenseNet201 model. The results could be used for area verification, real-time monitoring, and surface change detection. Nowadays, this is very helpful for Ukrainian territory because of the Russian invasion and the country's recovery in the future.

Land use-land cover dynamics, and local perceptions of change drivers among Nyangatom agro-pastoralists, Southwest Ethiopia

Understanding the spatio-temporal dynamics of land use and land cover (LULC) and their drivers is instrumental in synthesizing knowledge for informed natural resource management, planning, and associated decisions. The objective of this study was to analyze LULC dynamics and their drivers in the Nyangatom district of southwest Ethiopia. This study adopted a mixed-method approach, comprising remote sensing and geographic information system-based analysis, focus-group discussions, key informant interviews, and structured interviews covering 384 agro-pastoral households. Land use and land cover maps were compiled with Landsat image data from 1992, 1999, 2010, and 2020 using supervised pixel-based classification with a maximum likelihood algorithm. The study revealed that grassland (33%) and shrub land (27%) are the dominant LULC classes in the study periods. The results show a significant increase in settlement, cropland, and bare land, between 1992 and 2020 following demand for fertile lands, overgrazing, and climate changes. Reductions in the water body, open woodland, riverine forest, and dense woodland of − 23%, − 18%, − 18%, and − 7%, respectively, were observed for the same period with an overall accuracy of 80%. Agro-pastoralists identified agricultural expansion, overgrazing, and drought as the main drivers of LULC changes, followed by conflicts, invasion of alien plant species, and change in policy institutions. The impacts of unplanned LULC change can be reduced through appropriate land-use planning with genuine stakeholder engagement. Updated information on present and future LULC dynamics can support these social dynamics and align a shared understanding among stakeholders that replaces polarization and erosion of mutual trust.

Multiclass Land Use and Land Cover Classification of Andean Sub-Basins in Colombia with Sentinel-2 and Deep Learning

Land Use and Land Cover (LULC) classification using remote sensing data is a challenging problem that has evolved with the update and launch of new satellites in orbit. As new satellites are launched with higher spatial and spectral resolution and shorter revisit times, LULC classification has evolved to take advantage of these improvements. However, these advancements also bring new challenges, such as the need for more sophisticated algorithms to process the increased volume and complexity of data. In recent years, deep learning techniques, such as convolutional neural networks (CNNs), have shown promising results in this area. Training deep learning models with complex architectures require cutting-edge hardware, which can be expensive and not accessible to everyone. In this study, a simple CNN based on the LeNet architecture is proposed to perform LULC classification over Sentinel-2 images. Simple CNNs such as LeNet require less computational resources compared to more-complex architectures. A total of 11 LULC classes were used for training and validating the model, which were then used for classifying the sub-basins. The analysis showed that the proposed CNN achieved an Overall Accuracy of 96.51% with a kappa coefficient of 0.962 in the validation data, outperforming traditional machine learning methods such as Random Forest, Support Vector Machine and Artificial Neural Networks, as well as state-of-the-art complex deep learning methods such as ResNet, DenseNet and EfficientNet. Moreover, despite being trained in over seven million images, it took five h to train, demonstrating that our simple CNN architecture is only effective but is also efficient.