Land Classification Research Articles

Analysis and Prediction of Land Use/Land Cover Changes in Korgalzhyn District, Kazakhstan

Changes occurring because of human activity in protected natural places require constant monitoring of land use (LU) structures. Therefore, Korgalzhyn District, which occupies part of the Korgalzhyn State Natural Reserve territory, is of considerable interest. The aim of these studies was to analyze changes in the composition of the land use/land cover (LULC) of Korgalzhyn District from 2010 to 2021 and predict LU transformation by 2030 and 2050. Landsat image classification was performed using Random Forest on the Google Earth Engine. The combined CA-ANN model was used to predict LULC changes by 2030 and 2050, and studies were carried out using the MOLUSCE plugin. The results of these studies showed that from 2010 to 2021, there was a steady increase in the share of ploughable land and an adequate reduction in grassland. It is established that, in 2030 and 2050, this trend will continue. At the same time, there will be no drastic changes in the composition of other land classes. The obtained results can be helpful for the development of land management plans and development policies for the Korgalzhyn District.

Response of hydrological ecosystem services to land-use change and risk assessment in Jiangxi Province, China

Water bodies provide humans with important hydrological ecosystem services (HESs), directly or indirectly. Water yield, water conservation, and soil conservation are essential to HESs. Since China's reform and opening up, and with its rapid socio-economic development, land use in Jiangxi Province has undergone drastic change, resulting in threats to the ecological environment. This paper evaluates three HESs, water yield, water conservation, and soil conservation, in Jiangxi Province based on land use and rainfall data, quantifies the impacts of different land classes on each ecosystem, predicts future land use using the patch-generating land use simulation (PLUS) model, and finally, discusses the ecological risks in the study area. The following results were obtained: (1) The HESs in the basin increased and then decreased from 2000 to 2020, and the spatial distribution of water yield and water conservation was greatly influenced by rainfall. Soil conservation was mostly consistent with the elevation distribution. (2) Over time, the overall aggregation of HESs in the study area increased. There were small differences in the effects of various land uses on water yield and water conservation, and large differences in the effects on soil conservation. (3) The distribution of ecological risks was not affected by different land use strategies, with the lower ecological risk level 1 dominating. Most risk areas were present in Ganzhou, Ji'an, Shangrao, and Jiujiang. The ecological risk from urban sprawl (US) accounted for the most significant proportion, and that from the ecological protection (EP) strategy accounted for the lowest proportion. This study provides reference for sustainable land use development and ecological risk prevention in the study area.

Effects of land use changes on green water along upper and middle reaches of Huaihe River Basin

Study regionThe Upper and Middle Reaches of the Huaihe River Basin Study focusThe examination of the ramifications of alterations in land utilization on terrestrial water resources holds paramount importance in the realm of agricultural water resource management. Despite progress in understanding the cumulative impacts of land use on terrestrial water bodies, the understanding of the exact impacts of a single land use on terrestrial water bodies is still insufficient. In this investigation, the SWAT model was employed to meticulously delve into the ramifications of modifications in land use on the quantity of green water in the middle and upper stretches of the Huaihe River, with a focus on simulating the hydrological cycle. Furthermore, this inquiry introduces a novel coefficient of impact to scrutinize the repercussions of specific land use changes on terrestrial water bodies. New hydrological insights for the regionThe outcomes of the study unveil that albeit the spatial expanse of certain land use categories is restricted, their repercussions on terrestrial water bodies reverberate extensively. Ultimately, the classification of forest land and agricultural acreage underwent refinement, incorporating considerations of vegetation cover and crop typology. The inquiry establishes that the extent of forest land and the genre of crops cultivated on agricultural land stand as pivotal determinants of terrestrial water dynamics.

Assessment of Random Forest and Neural Network for Improving Land Use/ Land Cover Mapping from LIDAR Data and RGB Image: A Case Study of Magaga-El-Menia Governorate, Egypt

The goals of this article are to improve classification of land use/land cover information using LIDAR data and RGB images, as well as to compare the performance of various supervised machine learning classifiers (random forest and neural network) for extracting land use/land cover information. The 3D coordinates are first transferred to a high-resolution raster via interpolation. Height and intensity raster grids are formed. Second, various raster maps - a normalized digital surface model (nDSM), the difference of returns, and the LiDAR intensity image -are combined to create a multi-channel image. Five scenarios with different combinations were created. Finally, on the five separate datasets, several classifications based on random forest and neural network classifiers were performed. The classification findings were subjected to a quantitative accuracy check. A comparison of these five methodologies has been conducted. Following that, morphological operations were used to eliminate noise. The results revealed also that the fourth approach is the best followed by the third approach then the last approach then the second approach followed by the first approach. It was discovered that random forest classification outperforms neural network classification in terms of classification accuracy.

Multi-Year Time Series Transfer Learning: Application of Early Crop Classification

Crop classification is an important task in remote sensing with many applications, such as estimating yields, detecting crop diseases and pests, and ensuring food security. In this study, we combined knowledge from remote sensing, machine learning, and agriculture to investigate the application of transfer learning with a transformer model for variable length satellite image time series (SITS). The objective was to produce a map of agricultural land, reduce required interventions, and limit in-field visits. Specifically, we aimed to provide reliable agricultural land class predictions in a timely manner and quantify the necessary amount of reference parcels to achieve these outcomes. Our dataset consisted of Sentinel-2 satellite imagery and reference crop labels for Slovenia spanning over years 2019, 2020, and 2021. We evaluated adaptability through fine-tuning in a real-world scenario of early crop classification with limited up-to-date reference data. The base model trained on a different year achieved an average F1 score of 82.5% for the target year without having a reference from the target year. To increase accuracy with a new model trained from scratch, an average of 48,000 samples are required in the target year. Using transfer learning, the pre-trained models can be efficiently adapted to an unknown year, requiring less than 0.3% (1500) samples from the dataset. Building on this, we show that transfer learning can outperform the baseline in the context of early classification with only 9% of the data after 210 days in the year.

Assessment of Classification and Accuracy of Land Use/Land Cover in Jabalpur District, Madhya Pradesh, India: An Analysis by Remote Sensing and GIS Application

The main purpose of remote sensing is to prepare land use/ land cover (LULC) thematic maps through satellite image classification. So many researchers worked on various image classification techniques and accuracy assessment. LUCC change is posing a serious problem to earth’s ecosystems. One estimate puts the safe upper boundary for global cropland area to 15% of the total terrestrial area, a level that is only about three percentage point higher than current cropland area, which account for 12% of global land area (Anonymus, 2012). Objective of this study is to use remote sensing and GIS to prepare LULC map for the year 2016 in the Jabalpur district, Madhya Pradesh and to assess the accuracy of classified image. A multivariate rule is applied to carry out supervised classification. Five classes of LULC has been chosen to prepare the LULC map and areas coming under these classes are agriculture (59.26%), forest (18.28%) open/barren/wasteland (18.08%), waterbodies (2.68%) and built-up (1.70%). Overall classification accuracy of satellite image obtained in present study was 88.52 percent and kappa coefficient 0.80.

Urbanisation in Sub-Saharan Cities and the Implications for Urban Agriculture: Evidence-Based Remote Sensing from Niamey, Niger

Urbanisation is the process whereby cities are transformed into large sprawling areas. Urbanisation combined with a continuous increase in population makes food security crucial for sustainable development. Urbanisation poses a threat to agricultural land use within built-up and peri-urban areas. It has resulted in the rapid disappearance and/or total change of agricultural farmland in urban and peri-urban areas. To monitor the changes in agricultural farmland, an understanding of changes in the urban landscape is becoming increasingly important. In this study, multi-temporal Landsat imagery were used to analyse the impact of urbanisation on urban agriculture in the city of Niamey. Changes in the urban landscape were determined using the support vector machine (machine learning) algorithm. Results of this study showed a decrease in land with crops from 3428 ha to 648 ha and an increase in built-up areas from 1352 ha to 11,596 ha between 1975 and 2020. Urbanisation and population growth are the main drivers of urban landscape change in Niamey. There was also a decrease in bare land, rock and vegetation classes, while a small increase in rice and water body classes, comparing the 1975 and 2020 values. This study demonstrates the importance of remote sensing in showing the implications of urbanisation on urban agriculture. These results can assist city planners and resource managers in decision-making and adoption of sustainable mitigation measures which are crucial for urban development.

CHARACTERIZATION OF THE CHROMIC LUVISOLS PROFILE FROM SC AGROTEHNIC SRL, PAULESTI, PRAHOVA

The credit rating aims to establish the favorability classes of land for different agricultural crops.In this context, the present study aims to quantify the favorability of the Chromic Luvisols from S.C. Agrotehnic Paulesti for arable use. Also, this study has as a main objective a morphological characterization and profile description of Chromic Luvisols.Following the study, it can be concluded that it is presents the same limiting factors as for arable suitability related to the loamy-clay texture, which implies a short interval of soil works and the appearance of the hardpan sub-horizon.

Potencijal poljoprivrednog zemljišta prema katastarskom klasiranju na prostoru prirodnog dobra u postupku zaštite Predela izuzetnih odlika "Planina Rudnik"

During 2023, the Institute for Nature Conservation of Serbia submitted a proposal and an act on the designation of a protected area, the Outstanding Natural Landscape Rudnik Mountain, to the Ministry of Environmental Protection. 33.70% of agricultural land, which is recognized as a resource of economic development potential, is included within the boundaries of the proposed protected area. Based on information obtained from the Republic Geodetic Office's Real Estate Cadastre, an analysis of the cadastral classification of land by cadastral municipalities was conducted to determine the potential for success of this rural region with regard to agricultural activities. The cadastral classification of agricultural land is based on natural production conditions and follows the morphological, physical, chemical, biological and paedological-geological characteristics of the soil of the Rudnik Mountain, as well as the dynamics of the area: relief, altitude, inclination of the terrain, slope aspect, erosional processes and other conditions aligned with the Rulebook on land cadastral classification. The results of this analysis set the basis for future activities to improve the situation regarding the use and possible protection of agricultural land within ONL Rudnik Mountain.

Innovative approaches to qualitative land assessment and valuation: use of modern technologies and geoinformation x systems

The article examines modern methods and technologies that can be used to increase the accuracy of land valuation. The authors analyze the current problems in the field of rating and offer ways of integrating geoinformation systems with the aim of creating a more objective and information-rich picture of land quality. The purpose of the article. Study of the potential of using the latest technologies and geoinformation systems in determining the quality and classification of land with the intention of increasing accuracy and impartiality in the assessment of land resources. Research methods. During the research, the following methods were used: comparative analysis, the method of automated image decoding, the cartographic method and the geo-information mapping method. The results. The article emphasizes the importance of geoinformation systems in the collection, processing and analysis of data, which allows taking into account a wide range of factors when evaluating land, including erosion processes, soil fertility, ecological status and other critically important indicators. Special attention is paid to the possibilities of using remote sensing and other automated methods for data collection. Conclusions. The results of the research are of practical importance, as they can be used to optimize agricultural management, plan the use of land resources, and develop strategies for their effective use and protection. Prospects for further research may include the development of new algorithms for the analysis and processing of data obtained from satellite images, as well as the improvement of existing geoinformation models for land evaluation. Integration of the obtained models and systems into the practical aspects of land use and agricultural management is also envisaged to optimize the use of land resources and increase the efficiency of land use.

Improving the methodology for monitoring vegetation cover based on type segmentation

Monitoring is an important element for defining sustainable land cover management strategies. The monitoring technique proposed and developed in this work with integrated processing of remote sensing data has the potential to scale and optimize the interpretation of vegetation classes, making the analysis of the territory more detailed. This approach based on multiclass classification of composite images with data preprocessing based on Google Earth Engine (GEE) cloud platform. The article describes the characteristics and benefits of the uses cloud platform. Three regions, different in their characteristics and climatic features, were chosen as the study area: Voronezh Oblast, Republic of Tatarstan and Perm Krai. The objects of the study were the classes of forest vegetation, arable land and meadow vegetation. The article presents a step-by-step methodology for obtaining and processing Sentinel-2 satellite imagery data. The main steps of the methodology include obtaining a time series of satellite data and processing them, applying a vegetation index to satellite images, selecting reference data for validation, classifying objects using the random forests algorithm. An overview of WorldCover cartographic product from European Space Agency (ESA) and its advantages for use in working with geoinformation data is presented. The classification of target classes of vegetation in GEE cloud platform was carried out. The results of the study contain an analysis of a combination of normalized difference vegetation index (NDVI) for each studied class of vegetation. Implementation of the methodology is important for retrospective analysis and operational monitoring of vegetation cover classes. The method of multi-class segmentation of objects based on time series analysis will significantly improve the accuracy and speed of providing analytics to update information on land use.

Semi-Supervised Multi-Label Classification of Land Use/Land Cover in Remote Sensing Images With Predictive Clustering Trees and Ensembles

Semi-Supervised Multi-Label Classification of Land Use/Land Cover in Remote Sensing Images With Predictive Clustering Trees and Ensembles

Mapping cropland in Yunnan Province during 1990–2020 using multi-source remote sensing data with the Google Earth Engine Platform

Cropland is the foundation of agriculture and the cornerstone of ensuring national food security. Ongoing advancement of China’s urbanization and social economy results in a tendency toward ‘non-agriculturalization’ of cropland in pursuit of economic benefits, which greatly threatens food security. Therefore, long-term monitoring of cropland is urgently needed. Based on the Google Earth Engine (GEE) platform, this paper uses the Landsat series and Sentinel-2 multisource images from 1990–2020 to dynamically monitor cropland in Yunnan Province. First, a multiresolution collaborative sample selection method was proposed and sample labels with resolutions better than 30 m from 1990 to 2015 were obtained. An ‘impervious surface-spectrum-texture-geometry’ (ISTG) feature system was constructed and the Jeffries-Matusita (JM) distance method was used for feature optimization. Finally, the proposed collaborative classification system method of land classification and binary classification was used to extract cropland in Yunnan Province. The results show that: (1) The accuracy of cropland extraction was highly reliable, with an overall accuracy (OA) wall-to-wall ranging from 93.15–98.14% and a kappa coefficient (Kappa) ranging from 86.29–96.26%. (2) The change trend of the cropland area in Yunnan Province from 1990 to 2020 exhibited certain fluctuations, but overall decreased annually. (3) The province’s average annual cropland area is 567.71 × 103 hectares. The proposed method has great potential in large-scale cropland extraction.

Land Classification Research Based on the Improved Deeplabv3+ Model and the AI Earth Remote Sensing Cloud Platform

Land Classification Research Based on the Improved Deeplabv3+ Model and the AI Earth Remote Sensing Cloud Platform

A Joint Network of Super-Resolution and Active Learning for Agricultural Land Classification

A Joint Network of Super-Resolution and Active Learning for Agricultural Land Classification

Modeling projected impacts of climate and land use/land cover changes on streamflow in Gelana Catchment, Southern Ethiopia

Effective watershed management is extremely critical because changes in the global and local distribution of climate have a direct impact on ecosystems. The primary goal of the current study was to evaluate current and projected climate and land use land cover (LULC) change on streamflow in Gelana catchment. LULC prepared via supervised classification algorithm by using ERDAS (Earth Resources and Development Systems) software, ArcGIS 10.4 (for satellite image processing and map preparation), and the Cellular Automata (CA)-Markov model revealed significant gains in agricultural and built-up over forest and pasture land classes. A coordinated regional climate downscaling experiment under the Africa domain for three regional climate data for two future scenarios (RCP 4.5 and RCP 8.5) showed a significant reduction in rainfall from 48.64 % to 4.6 %, while minimum and maximum temperatures increased from 0.58 to 3.35 °C and 0.5 to 2.93 °C, respectively. The Soil and Water Assessment Tool (SWAT) model was applied to analyze the impact of LULC and climate change on streamflow. The model calibration and validation were carried out by using monthly observed streamflow for the most sensitive parameters by using Sequential Uncertainty Fitting (SUFI-2) within the SWAT Calibration of Uncertainty Program (SWAT-CUP). The model performed well between observed and simulated streamflow, with R2, NSE, PBIAS, P, and r-factors of 0.84, 0.77, −15.9, 0.68, and 0.56 for calibration and 0.88, 0.8, −14, 0.63, and 0.65 for validation, respectively. The results of the study implied the simulated mean annual streamflow increased from 3.22 % to 23.82 % in the case of LULC change alone, while it decreased from 38.2 % to 23.27 % for climate change alone for the near-term of RCP 4.5 and from 45.3 % to 24.6 % for RCP 8.5. Further substantial decline was observed in the combined simulation, from 55.38 % to 42.45 % and 62.15 % to 59.36 % for the near and far future of RCP 4.5 and RCP 8.5, respectively. In order to address the constraints, current findings are valuable to scale up sustainable natural resource management.

A regional-level spatiotemporal perspective of land use and land cover change impact on forest aboveground biomass in three gorges reservoir region, China

This study used multi-platform remote sensing datasets to assess the impacts of land use and land cover (LULC) change on forest biomass density across the Three Gorges Reservoir (TGR) region along the Yangtze River. This study maps land use and land cover (LULC) change and forest aboveground biomass estimation (AGB) using Sentinel-2A and GEDI-L4B data based on observations between 2019 and 2022. The data analysis results of monitoring revealed a strong association frequency between land-use change and forest land cover since the significant relationship with forest aboveground biomass density has also been explored. The total deforestation decreased significantly in 2022. The accuracy assessment results show a classification accuracy of between 90.4% and 94.1%, with a kappa coefficient of 82.4%–92.1%. For the TGR region forest, the minimum to maximum mean above-ground biomass values are from 15.81 to 373.66 Mgha-1, respectively. Moreover, the fitting performance of the statistical analysis of aboveground biomass density of forest mean for the forest was quite decent with training (R 2: 0.92, RMSE: 12.30 Mg/ha) and testing (R 2: 0.79, RMSE: 18.07 Mg/ha) datasets. The results highlight LULC change impacts, particularly forest land class over forest AGB stands, and the effectiveness of the GEDI-L4B product in regional biomass estimation in the TGR region.

AGRO-ECOLOGICAL CLASSIFICATION OF AGRICULTURAL LAND USING MACHINE LEARNING, GIS AND REMOTE SENSING DATA

The paper is devoted to agro-ecological classification of agricultural land using modern methods of geo-information data analysis and machine learning.
 Background. There are few works in the literature, which cover the issues of accuracy of machine learning (MLL) models for agro-ecological grouping of agricultural land. A large number of raster information layers are used to improve the accuracy of land classification from satellite images. This considerably increases the time of training and testing MMOs, producing thematic maps of agricultural land classification. This approach requires considerably high computing resources and a considerable amount of computer RAM. Raster GIS data models occupy a much larger volume than vector models. In this regard, research on automated agro-ecological (grouping, classification) of agricultural land using vector GIS models is of practical importance.
 Purpose. The aim of the study is to apply GIS methods, remote sensing (ERS) data and machine learning methods for agricultural land grouping.
 Materials and methods. The materials used were synthesized multispectral high spatial resolution Sentinel-2A images, maps of vegetation indices NDVI (Normalized Difference Vegetation Index), OSAVI (Optimized Soil Adjusted Vegetation Index), EVI2 (Enhanced Vegetation Index2), NDWI (Normalized Difference Water Index), SAVI, PVI, GDVI, MCARI, NDRE, TSAVI; topographic map, ALOS DSM (30 m/pixel) and ALOS PALSAR (12.5 m/pixel) satellite images, soil map and field survey results. Field measurements were carried out using the Triump-2 satellite geodetic receiver and included determination of coordinates of characteristic points of land plot boundaries, relief elements, and soil survey.
 Digital spatial model of land use was created using GIS ArcGIS and QGIS, Python engineering libraries were used in the machine learning process.
 Results. Agro-ecological grouping of lands was realized by the example of the farm "Zerno Sibiri" of Novosibirsk region using the following machine learning methods: Random Forest (RF) method, Decision Tree (DT), k-nearest neighbours method (KNN). The best accuracy is the RF machine learning model. The accuracy of the model averaged 97.9% (with training 99.9%, testing 98.8%, and cross validation 95.0%). The Root Mean Square Error (RMSE) is 0.006: for training sample 0.001; test sample 0.076; validation sample 0.123 respectively). The mean kappa coefficient was 0.97 (1.00 for the training sample; 0.982 for the test sample, and 0.927 for the validation sample). 
 Conclusion. The offered method of agro-ecological grouping of agricultural lands by means of GIS, RS data and machine learning methods enabled to distinguish informative quantitative indicators of the relief. The main essence of the proposed method is to create a machine learning model (MLM) based on a spatial dataset. The spatial dataset is formed using geoinformation analysis methods and includes: geomorphometric maps, maps of agrometeorological parameters, soil map, on-farm land management map and operational-territorial units of land classification. The application of vector data model allowed for agro-ecological grouping of agricultural lands in automated mode, to accelerate labor-intensive process of raster data recognition, to increase objectivity of the work. The suggested method of agro-ecological agro-ecological grouping of lands allows taking into account the totality of relief and soil-ecological conditions indicators with the help of geoinformation analysis methods, remote sensing and machine learning.

The Impact of Changes in Land Use on Green Open Space and Comfort Index in Semarang City, Indonesia

Semarang City is one of the cities with the most dense population in Indonesia. The increase in the population of Semarang City causes land conversion which has an impact on increasing heat and can cause environmental problems. The results of the random classification of forests for land use in 2013-2022 are dominated by the built-up land class. Use of built-up land continues to increase from 2013-2022 by 8.84% or an area of 3410 ha. This causes a reduction in green open space by 7.59% or an area of 2928.49 Ha and is still sufficient by 30%. In the predicted use of land in 2032, the dominance of the built-up land class is 61% (23,575 ha). The availability of green open space (RTH) in Semarang City continues to decline from 2013-2032 by 9%. Where in 2032 the availability of green open space will be 29.62% or less than 30%. The relationship between green open space and comfort levels influences each other, where a reduction in green open space causes an increase in comfort levels. Directions need to be made for developing green open spaces consisting of priority 1 areas, namely adding green open spaces in each sub-district, maintaining existing green open spaces, and creating roof gardens and vertical gardens to reduce temperatures in densely populated areas. Meanwhile, priority area 2 is maintaining existing green open space in the form of urban forests and plantation areas.

Представяне на „Софтуер за потенциална относителна оценка и класификация по пригодност за земеползване на земеделските земи в България“

In 2023, I developed “Software for potential land use suitability classification of agricultural land in Bulgaria” (Radovanova, 2023). It works in MS Office terms, programmed entirely through Microsoft Excel. The software with the corresponding methodology is essentially an update of the legally adopted “Methodology for work on the cadastre of agricultural land in Bulgaria” (Petrov E. et al., 1988), and this was achieved by a newly developed “Methodology for potential assessment of agricultural land in Bulgaria” (Radovanova, 2020). Actual and potential assessment are fully comparable in terms of approach, scheme, parameters, etc. The difference between actual and potential assessment, as in the case of software, is that in the case of potential assessment of agricultural land, potential characteristics (subject to improvement by external intervention) are used. These characteristics are: depth of the humus horizon, soil reaction, humus content, groundwater level, stoniness of the plough soil and degree of salinity and/or alkalinity. For these characteristics, 86 newly developed Bonite scales and algorithms have been applied (Radovanova, 2020). The software uses the built-in functions of Microsoft Excel. The mechanism of the existing final land use suitability categorisation of the assessed land is fully maintained, but is now considered in a “potential” aspect and uses the new potential algorithms. The software allows the printing of an official document of the potential assessment of the agricultural land concerned.