Land Cover Map Research Articles

High-Resolution Land-Cover Mapping Based on a Cross-Resolution Deep Learning Framework and Available Low-Resolution Labels

High-Resolution Land-Cover Mapping Based on a Cross-Resolution Deep Learning Framework and Available Low-Resolution Labels

Mapping Land-Cover Dynamics in Arid Regions Using Spectral Mixture Analysis and Representative Training Samples

Mapping Land-Cover Dynamics in Arid Regions Using Spectral Mixture Analysis and Representative Training Samples

NILE CROCODILE NESTING ECOLOGY UNDER VARYING HUMAN DISTURBANCE INTENSITIES ALONG LOWER RIVER TANA, KENYA

The Nile crocodile (Crocodylus niloticus, Laurenti, 1768) supports important ecological and socio-economic functions; however, its survival in most of its ranges in Africa continues to be threatened by anthropogenic activities. Here, we compared selected attributes of Nile crocodile nests (abundance, clutch size, distance from water, and presence or absence of eggs, tending and predation) across three human disturbance regimes (low, intermediate and high), indexed by coverage of cropland and settlement, along lower River Tana, Kenya. We conducted a crocodile nest survey in January 2019 and overlaid the resultant data on the most recent land cover map of a 1-km wide strip on both sides of the river, segmented into the different disturbance regimes using remote sensing and geographical information system techniques. The low, intermediate and high disturbance regimes comprised combined cropland and settlement coverage of 2%, 9% and 15%, respectively, and covered 28%, 27% and 47% of the surveyed river segment. We counted a total of 99 nests, with 45, 34 and 20 nests located in low, intermediate and high disturbance regimes, respectively. Nests were 56% less frequent than expected under high disturbance, whereas they were 69% more frequent than expected under low disturbance and showed expected frequency under intermediate disturbance. In addition, nests were 56% and 41% less frequent under high disturbance compared to low and intermediate disturbance, respectively. However, nest abundance was statistically similar between the latter two regimes. No significant differences were observed in other assessed attributes across disturbance regimes. Our study underscores the importance of minimizing land conversion in such human-dominated landscapes for enhanced sustainable utilization and conservation of crocodiles.

Evaluation of Different Machine Learning Algorithms for Land Cover Mapping: A Case Study of Izmir Province

Doğal kaynak yönetimi ve mekânsal planlama süreçlerinde ayrıntılı, güncel ve doğru bilgilere dayanan arazi örtüsü ve arazi kullanımı (AÖAK) durumunun tespiti önemli rol oynamaktadır. Ancak, bölgesel ölçekte arazi kullanım dinamiklerinin izlenmesini engelleyen veri işleme süreci ve depolama gereksinimi gibi bazı sınırlılıklar vardır. GEE, küresel ölçekte coğrafi verilerin işlenmesine olanak tanıyan açık kaynak kodlu, ücretsiz bir bulut platformdur. Bu araştırmanın amacı GEE üzerinde farklı makine öğrenmesi algoritmaları ile İzmir ili AÖAK haritasını elde etmek ve kullanılan sınıflandırma algoritmaların sonuçlarını karşılaştırmaktır. Araştırmada 2022 yılına ait 10m mekânsal çözünürlüğe sahip Sentinel-2 çok bantlı uydu görüntüleri ile çeşitli UA indeksleri kullanılmıştır. Araştırmada kullanılan geniş ölçekteki AÖAK sınıfları ‘Tarım Alanı’, ‘Orman Alanı’, ‘Beşeri Yüzeyler’, ‘Açık Yüzeyler’ ve ‘Su Yüzeyleri’ şeklinde belirlenmiştir. Çalışmada Sınıflandırma ve Regresyon Ağacı (SRA), Destek Vektör Makinesi (DVM), Rastgele Orman (RO) makine öğrenmesi algoritmaları kullanılmış ve her bir sınıflandırıcının Üretici Doğruluğu (ÜD), Kullanıcı Doğruluğu (KD) ve Genel Doğruluğu (GD) ile Kappa Katsayısı hesaplanmıştır. Sonuç olarak %97,2 GD ve Kappa değeri %95,7 olan RO sınıflandırma algoritması, en yüksek sınıflandırma doğruluğuna sahiptir. %96,1 GD ve %94,9 Kappa değeri ile DVM algoritması ikinci en yüksek sınıflandırma doğruluğuna sahip algoritma olmuştur. SRA algoritmasının GD %93,3, Kappa değeri ise %91.4 olarak hesaplanmıştır. Sonuç olarak RO yöntemi SRA ve DVM yöntemlerine göre daha iyi sonuç verdiği tespit edilmiştir. Diğer yandan sınıflandırma modellerinde özellikle açık yüzeyler ile beşeri yüzeyler ve çıplak tarım alanları arasındaki yansıma örtüşmesi bu sınıfların ayırt edilmesini güçleştirdiği görülmektedir.

Satellite Nighttime Light and Digital Elevation Data to Assess Urban Expansion in Floodplains of Dhaka City

This study aims to evaluate the potential of DMSP/OLS nighttime light data to investigate human presence and activity in Dhaka City, Bangladesh. The study explores the sensor's ability to detect and monitor urban expansion patterns and human presence and activity at a regional scale. Thematic land cover maps revealed a rapid expansion of built-up areas within the 43-year study period, increasing from 35 km² in 1972 to 378 km² in 2015, representing a net gain of approximately 980% and an average annual growth rate of 6%. Notably, this growth rate was significantly higher in peripheral areas (2903% and a yearly expansion rate of 8%) compared to the central city area (Dhaka City Corporation) (460% and an annual expansion rate of 4%). This substantial urbanisation has primarily occurred in Dhaka's northern, northwestern, and southwestern sectors, transforming previously agricultural land, vegetation cover, wetlands, and water bodies. The findings demonstrate the utility of DMSP/OLS imagery for detecting human activities and presence in the Dhaka region, providing valuable insights into urban expansion patterns and their implications for environmental and social dynamics.

Exploration of Resnet Variants in High Spatial Resolution Domain Adaptation

Abstract. When mapping land cover from airborne to spaceborne data, a problem arises, where the difference in sensors between the two shows a large spatial resolution inconsistency and spectral differences. Consequently, the same object may exhibit completely different features. This problem causes models trained from annotated airborne to be ineffective when applied to spaceborne. Cross-Sensor Land-COVER (LoveCS) shows good results in overcoming this problem. LoveCS leverages small-scale aerial image annotations to promote land cover mapping on large-scale spacecraft. LoveCS uses ResNet50 as its encoder. In recent years, many studies have tried to develop other variants of ResNet, such as ResNeXt, ResNeSt, Res2Net, and Res2NeXt. This variation of ResNet turned out to give better results in a variety of tasks compared to ResNet. Therefore, in this study we modified the LoveCS encoder by replacing ResNet50 with ResNet variants such as ResNeXt, ResNeSt, Res2Net, and Res2NeXt in an effort to improve LoveCS accuracy. We also offer LoveCS schemes with better accuracy based on the best encoders. Our evaluation shows that Res2Net50 as an encoder is able to improve LoveCS performance where the average F1 increases by 1.38%, OA by 1.96%, and Kappa by 2.75% from the baseline method.

Land cover change analysis of buffer areas in New Capital City of Nusantara, Indonesia: A cellular automata approach on satellite imageries data

The proposed plan to move Indonesia's capital city to the New Capital City of Nusantara in East Kalimantan Province undoubtedly requires careful efforts to ensure food supply for the population. Population migration to the new capital may pose a food security challenge. To address this fundamental issue, one of the most crucial approaches is to establish buffer areas that can support the food needs of the new capital. The currently existing official Area Sampling Frame survey conducted by the government to assess food vulnerability faced several limitations, including weather conditions, field terrain variations, and high cost. In this study, we propose the utilization of remote sensing satellite imagery data in buffer areas to analyze changes and predict future land cover, which can provide valuable data for assessing food availability. We investigate the integration of a Cellular Automata method with the two most popular analytical methods of classical Logistic Regression and data-driven Artificial Neural Networks, known as CA-LR and CA-ANN, to identify and map land cover changes in the new capital buffer zones. Our findings reveal that both combined methods, CA-LR and CA-ANN, yield fairly promising results, with correctness and kappa statistic values exceeding 80%. Prediction results indicate that buffer areas are predominantly covered by trees, while built-up areas are still limited. The flooded vegetation cover, including rice fields, is predicted to decrease by 2024. This should be a matter of concern for stakeholders, considering the construction of the new capital city is still ongoing and the number of migrants is expected to keep rising.

Mapping Pinus spp. Forestry and Land Cover Classes Using High-resolution PlanetScope Satellite Data: Experimenting Images from Different Seasons and Machine Learning Methods

The Remote Sensing and machine learning techniques are cost-effective ways of mapping land use and cover, especially forestry areas. This is essential for the management and planning of such resources. The purpose of this study was to identify which classifier (Random Forest or Support Vector Machine) reach the best accuracy in land use and cover classification and determine which is the best season of year for Pinus spp. forest mapping. PlanetScope multispectral image was used with 3.7 m of spatial resolution, collected over the coastal region of Rio Grande do Sul state. The input variables for the classifiers were the four spectral bands: RGB and NIR, and the NDVI vegetation index. In both classifiers, high accuracy values were obtained, as well as for all seasons of the year. The Random Forest classifier obtained better results in the spring and summer seasons, while in the autumn and winter seasons there was no significant difference between the classifiers for the classification of Pinus spp. forests. The results reached an adequate precision to be used for the management and monitoring of the land use and cover in the municipality of São José do Norte, RS.

Land Use Change Modelling Using Logistic Regression, Random Forest and Additive Logistic Regression in Kubu Raya Regency, West Kalimantan

Kubu Raya Regency is a regency in the province of West Kalimantan which has a wetland ecosystem including a high-density swamp or peatland ecosystem along with an extensive area of mangroves. The function of wetland ecosystems is essential for fauna, as a source of livelihood for the surrounding community and as storage reservoir for carbon stocks. Most of the land in Kubu Raya Regency is peatland. As a consequence, peat has long been used for agriculture and as a source of livelihood for the community. Along with the vast area of peat, the regency also has a potential high risk of peat fires. This study aims to predict land use changes in Kubu Raya Regency using three statistical machine learning models, specifically Logistic Regression (LR), Random Forest (RF) and Additive Logistic Regression (ALR). Land cover map data were acquired from the Ministry of Environment and Forestry and subsequently reclassified into six types of land cover at a resolution of 100 m. The land cover data were employed to classify land use or land cover class for the Kubu Raya regency, for the years 2009, 2015 and 2020. Based on model performance, RF provides greater accuracy and F1 score as opposed to LR and ALR. The outcome of this study is expected to provide knowledge and recommendations that may aid in developing future sustainable development planning and management for Kubu Raya Regency.

The Use of Artificial Intelligence and Satellite Remote Sensing in Land Cover Change Detection: Review and Perspectives

The integration of Artificial Intelligence (AI) and Satellite Remote Sensing in Land Cover Change Detection (LCCD) has gained increasing significance in scientific discovery and research. This collaboration accelerates research efforts, aiding in hypothesis generation, experiment design, and large dataset interpretation, providing insights beyond traditional scientific methods. Mapping land cover patterns at global, regional, and local scales is crucial for monitoring the dynamic world, given the significant impact of land cover distribution on climate and environment. Satellite remote sensing is an efficient tool for monitoring land cover across vast spatial extents. Detection of land cover change through satellite remote sensing images is critical in influencing ecological balance, climate change mitigation, and urban development guidance. This paper conducts a comprehensive review of LCCD using remote sensing images, encompassing exhaustive examination of satellite remote sensing data types and contemporary methods, with a specific focus on advanced AI technology applications. Furthermore, the study delves into the challenges and potential solutions in the field of LCCD, providing a comprehensive overview of the state of the art, offering insights for future research and practical applications in this domain.

Analysis of Stormwater and Rainwater Harvesting Potential Based on a Daily Water Balance Model: A Case Study of Korea

The increasing intensity of rainfall resulting from climate change is projected to worsen the inundation of urban areas by floods. As a viable alternative, stormwater harvesting presents an opportunity to enhance water supply reliability while reducing pressure on both water resources and urban stormwater drainage systems. The stored rainwater can be supplied with a radius of one kilometer around the storage facility, so less pumping energy is consumed compared to supplying the stored rainwater far away from the storage facilities. To visually depict the characteristics of the selected storage facility, land cover maps were created using ArcGIS. These maps were created for a circular region with a radius of one kilometer around each studied storage facility. In this study, a daily water balance model was formulated using spreadsheets to assess the potential of harvesting stormwater and rainwater for various pre-existing storage facilities. Five different types of storage facilities were selected for this study. The term “SRWH facility evaluation criteria” as a whole is used for the storm or rain (SR) water supply satisfaction rate, the SR guarantee rate, and the SR utilization rate. The results provide evidence that, for each selected studied storage facility, the SR water guarantee rate can potentially surpass 70% under conditions of low water demand. Moreover, we investigated the potential of the existing storage facilities to work as multifunctional resources, while the original purpose for which each facility was constructed remains un-affected.

Flood Impact Assessment in Koton Karfe Using Sentinel-1 Synthetic Aperture Radar (SAR) Data

Flood has proven to be an incessant menace in Nigeria more threatening to riverine areas. The most recent flood ensued in 2022 as a result of heavy rainfall and the release of water from Lagdo Dam in Cameroon which became very devastating in many areas notably the Koton Karfe area in Kogi State, causing business shutdowns and the loss of lives and properties. In this work, Sentinel-1 Synthetic Aperture Radar (SAR) imagery was used for flood inundation mapping, and the accompanying damages were investigated using Landsat derived Land cover maps of Koton Karfe during the 2022 devastating flood. Overall, the results obtained in this study show that the regions that felt the impact of the flood the most were the southern and western areas, which must have experienced such an impact due to their proximity to the rivers Niger and Benue and also the water coming from the upper stream part of Cameroon. Further findings revealed that during the flood period on October 13, 2022, the total inundated area in Koton Karfe was estimated to be 198.255 sq. km. In terms of damage assessment, the urban areas had reduced from 220.902 sq. km in May 2022 to 87.473 sq. km in November 2022. This shows that over 133 sq. km of the urban settlement have been lost, indicating that lives must have been lost, properties too, and humans must have been displaced. This research will assist in the space of flood emergency response and disaster management.

Identification of Deforestation in Protected Forest Areas Using Land Cover mapping (A Case Study of Bukit Suligi Protected Forest)

In order to identify deforestation in Protected Forest Areas, land cover mapping has been used as a relevant method. This research aims to identify and map deforestation rates around the Bukit Suligi Protected Forest Area, as well as changes in land cover classes that occurred during the 2015-2022 period. The results showed that the deforestation rate reached 1,362.55 hectares per year or about 10.45% per year, a very alarming figure. This indicates a serious threat to forest sustainability and biodiversity in the area.

Impact of land use/land cover changes on evapotranspiration and model accuracy using Google Earth engine and classification and regression tree modeling

This research uses a Classification and Regression Tree (CART) model with Google Earth Engine (GEE) to assess the winter season’s land cover and change detection mapping impact on the evapotranspiration (crop water requirement) parameters. Winter seasons, crucial for agricultural planning, and irrigation water requirement challenges in accurately mapping land cover and detecting changes due to the dynamic nature of farming practices during this period. In this study, Landsat-8 OLI images have been combined to map Land use and Land cover (LULC) and other change detection mapping in Akola Block, Maharashtra, India, during the 2018–2022 winter season. As an discoverer researcher that found detailed information of LULC classes during last 2018 to 2022 winter seasons, the use of the CART model in combination with a cloud-computing GEE demonstrates to be a practical approach for accurate land cover classification and change detection maps to create a pixel-based winter seasons information of study area. The novelty of this study lies in its innovative use of GEE, a powerful platform for remote sensing and geospatial analysis, to create LULC maps with remarkable accuracy. Achieving a 100% training accuracy across the four years under consideration is an exceptional feat, highlighting the reliability and stability of the methodology. Furthermore, the validation accuracy values, ranging from 89 to 94% for the winter seasons of 2018 to 2022, underscore the robustness of this approach. Such consistently high accuracy in mapping LULC over time is a groundbreaking achievement and offers a new dimension to the field of hydrology. For the hydrological community, the implications of this study are profound. Accurate LULC mapping and change detection provide critical data for modeling and analyzing the effects of land use changes on water resources, watershed management, and water quality. The User, Kappa, and Producer accuracy metrics used in this research highlight the model’s performance and its suitability for hydrological applications. These accurate LULC maps can aid in the development of hydrological models, forecasting, and decision-making processes, ultimately contributing to more effective water resource management and environmental conservation. In summary, this study’s innovative use of GEE, its remarkable accuracy in LULC mapping, and its relevance to the hydrological community demonstrate the potential for advanced remote sensing and geospatial tools to significantly improve our understanding of land use changes and their implications for water resources and environmental management.

Continuous Time-Series Land Cover Maps for South Korea using Google Earth Engine

In this study, we utilized Google Earth Engine to construct, for the first time in South Korea, a long-term (1986-2021) continuous time series of land cover maps with a spatial resolution of 30 meters. Derived from the surface reflectance data of the Landsat satellite series, a total of 44 input variables were generated, including various spectral bands and indices related to land cover. For accuracy verification of the maps, 4,824 reference data were established using areas where land cover remained unchanged, identified by comparing the most recent (2018) and historical (1988) land cover maps from the Ministry of Environment. The Random Forest model was employed to classify seven land cover types (settlements, cropland, forest land, grassland, wetlands, bare land, and water bodies), with an overall accuracy of 0.97 and a Macro F1-score of 0.91, indicating a generally high performance of the model. However, considering the annual variability, potentially due to unidentified or untraceable errors, a composite land cover map dataset, integrated in five-year intervals, was suggested to ensure the generation of stable data.

Soil Erosion Risk Assessment in The Niğde Using Corine Model

Soil erosion risk was calculated using the coordination of information on the environment (CORINE) model in this study. The aim of the study is to determine the soil erosion risk of Niğde province, taking into account soil properties, slope and land use. Potential (PSER) and actual soil erosion risks (ASER) were determined using factors which were soil properties, slope, climatic factors, and land cover data. Data were produced using Arc-GIS 10.3 software, and results were obtained on these maps. 34.72% of the soils were classified as moderately actual soil erosion risk, which located in the eastern and southeast part of the study area.51.66% and 13.62% of the soils were classified as low and high actual soil erosion risk, respectively. Areas which have low actual soil erosion risk are located in the middle part, and areas which have high actual soil erosion risk are located in the northwest part of the area. The areas which were categorized as low potential soil erosion risk were increased from 23.52% to 51.66% in the actual soil erosion risk, after combining the land cover map. On the other hand, the total areas classified as high and moderate actual soil erosion risk decreased from 76.48% to 48.34% in the actual soil erosion risk due to land cover types. Soil texture, land cover, and slope are the most important factors that affect erosion risk. This study indicated that the CORINE model integrated with GIS (Geographic Information Systems) and RS (Revised Universal Soil Loss Equation) has a very effective and accurate potential for soil erosion risk assessment.

Association of residential land cover and wheezing among children and adolescents: A cross-sectional study in five provinces of China

The association between residential land cover (RLC) and wheezing remains poorly understood. This study aimed to investigate the association between RLC and wheezing in childhood and adolescence. A cross-sectional survey was conducted among children and adolescents in five provinces of China. Land cover data were obtained from the Cross-Resolution Land-Cover mapping framework based on noisy label learning, classifying land cover into five categories: cropland, forest, grass/shrubland, wetland, and impervious. Generalized linear mixed models were employed to estimate odds ratios (ORs) and 95% confidence intervals (CIs) for the risk of wheezing. Mediation analysis was employed to investigate whether ambient particulate matter (PM2.5) acts as a mediator in the association between RLC and wheezing. A total of 12,875 participants were included in the study, comprising 318 patients and 12,557 controls. Cropland500m was significantly associated with decreased odds of wheezing (OR: 0.929, 95% CI: 0.879–0.982), while impervious surfaces500m significantly was associated with increased odds of wheezing (OR: 1.056, 95% CI: 1.019–1.096) in all participants. In the stratified analysis, significant differences were found in the main outcomes between the adolescence group (age ≥10 years) and the childhood group (age <10 years) (Pinteraction < 0.05), while no significant differences were observed between the southern and northern regions, or between male and female respondents. Mediation analysis revealed that PM2.5 partially mediated the association between cropland500m and impervious surfaces500m with wheezing. RLC plays a significant role in wheezing during childhood and adolescence, with cropland offering protection and impervious surfaces posing a heightened risk.

UPDATING ABOVEGROUND BIOMASS AT A PAN-EUROPEAN SCALE THROUGH SATELLITE DATA AND ARTIFICIAL INTELLIGENCE

Abstract. In this work, an ensemble of machine learning algorithms was trained using stratified sampling from an existing European-scale biomass map from 2018 to predict an updated version for 2020. The objective of stratification is to make sure that the full range of biomass values is represented. The sampled biomass values from 2018 were filtered to remove areas that did were subject to forest disturbances between 2018 and 2020. This information was available from forest cover/loss/gain maps derived from satellite imagery. We train using a total of 49 features derived from the following sources: bioclimatic data, maps of land-cover, tree cover, tree height, annual composites of vegetation indices per pixel (EVI and NDVI) obtained from Sentinel-2, radar backscatter median annual values from Sentinel-1 and ALOS-2, and the ALOS DSM (3D) elevation grid. A model was created dividing Europe into 19 tiles to limit variability due to very different bioclimatic zones. The result is a raster with 100 m × 100 m resolution and an estimated value of biomass (Mg ha−1) at each node. Overall results on validation data over Europe report a root mean square error (RMSE) of 32.4 Mg ha−1 and a mean absolute error (MAE) of 21.5 Mg ha−1; when considering single tiles, the largest RMSE was 54.7 Mg ha−1 in tile D2, which can be explained by the very high variance of climate, environment, terrain topography and biomass values as the tile enclosed the Alpine region and the western part of Eastern Europe.

MAPPING BEE-KEEPING FOREST PLANTS FROM MEDIUM SPATIAL RESOLUTION MULTISPECTRAL SATELLITE DATA

Abstract. Apiculture is one of the main branches of agriculture and crucial to rural development since it provides farmers with unique products like honey, wax, pollen, royal jelly, propolis and bee venom. Due to pollination services provided by honeybees, environmental sustainability and diversity are also increased, as well as crop production. In Greece, approximately 2.000.000 bee colonies (second in the E.U.) are reported with a relatively high density per km2. There are more than 20.000 beekeeping operators that produce about 20.000 tons of honey every year, while more than 65% of Greek honey is produced from honey dew. To this end, this study aims to identify and map major honeybee flora in the Greek mainland and the Greek islands (Fir forests, Pine forests and Oak forests) for the year 2019, in order to examine best regions to deploy honeybee colonies. In particular, a classification framework for mapping the main honeybee flora is introduced that is exploiting annual moderate-resolution satellite multi-temporal data. Additionally, a methodology is presented to generate a coarser training dataset by utilizing a high-spatial resolution, detailed land cover map. This process specifically focuses on the integration of honeybee flora classes that are not present in the land cover map but are of significant great importance for honey flora mapping. The goal was to enable large-scale classification without the computational resource constraints typically associated with such national scale frameworks. Experimental results are quite promising with the quantitative validation indicating overall accuracy of more than 85%.

THE EFFECTS OF LAND COVER CHANGES ON LAND SURFACE TEMPERATURES

Abstract. The aims of this study are to detect the land-cover maps and land surface temperatures using Landsat time series and analyse the relation between the land-cover and land surface temperatures (LST) and their changes in time. For these purposes initially, land-cover maps were generated rapidly using land cover indices and automatic thresholding. The land-cover indices used in this study are Normalized Difference Vegetation Index (NDVI), Modified Normalized Difference Water Index (MNDWI), Index-Based Built-Up Index (IBI), Modified Bare-Soil Index (MBI), Plastic-Mulched Landcover Index (PMLI), Plastic Greenhouse Index (PGI) and Normalized Burn Ratio Thermal (NBRT) Index. Then, using the thermal bands of Landsat satellites, LST maps were created. Finally, the land-cover and LST changes were examined. The Kumluca district of Antalya, which includes extensive greenhouse areas as well as urban, vegetation, bareland, water, was selected as study area. Between the years 2004 and 2021, within the study area the greenhouse areas increased significantly, the urban area expanded and some areas exposed to fire, especially the fire in 2016. Therefore, the images within this time period were used. The overall accuracies for land-cover maps were computed as 76%, 79%, 79%, 89% and 86% for the years 2004, 2009, 2013, 2017 and 2021, respectively. The results obtained from the study reveal that while greenhouse and urban areas were increased, the vegetation areas were decreased significantly within this time period. In addition, generally increases were observed for LST values of all land-cover classes and the highest LST values were detected for the burned, bareland, urban and greenhouse areas.