Satellite Images Research Articles

The convergence of big data and SRE in modern agriculture: Transforming farming through technology

This article examines the transformative integration of Big Data analytics and Site Reliability Engineering (SRE) principles in modern agriculture. The article explores how precision agriculture leverages advanced technologies including IoT sensors, drone surveillance, and satellite imagery, to revolutionize traditional farming practices. It analyzes the implementation of sophisticated data collection infrastructures, Big Data systems, and SRE practices in agricultural settings. The article investigates the operational benefits and sustainability implications of these technological integrations, highlighting improvements in resource optimization, yield enhancement, and environmental conservation. Furthermore, it discusses future perspectives in agricultural technology, including edge computing applications, AI-driven autonomous systems, blockchain integration, and climate change adaptation strategies.

Upper quantile-based CUSUM-type control chart for detecting small changes in image data

Image monitoring is an important research problem that has wide applications in various fields, including manufacturing industries, satellite imaging, medical diagnostics, and so forth. Traditional image monitoring control charts perform rather poorly when the changes occur at very small regions of the image, and when the changes of image intensity values are small in those regions. Their performances get worse if the images contain noise, and the changes occur near the edges of image objects. In applications such as manufacturing industries, the changes in the images are often too small to be detected by human eyes. In this article, we propose a CUSUM-type control chart for online monitoring of grayscale images. Depending on what kind of changes we wish to detect, big or small, we propose to use a certain upper quantile of the local CUSUM statistics. We incorporate a state-of-the-art jump preserving image smoothing technique in the proposed chart that ensures good performance even in presence of low to moderate noise. Theoretical justifications, and superior performance in numerical comparisons ensure that the proposed control chart can be useful to many researchers and practitioners.

(Semi-)automatic Extraction of Urban Planning Rules in French for Better Management of Land Artificialization

Land artificialization is a significant modern concern, as it is irreversible, diminishes agriculturally suitable land and causes environmental problems. Our project, Hérelles, aims to address this challenge by developing a framework for land artificialization management. In this framework, we associate urban planning rules in text form with clusters extracted from time series of satellite images. To achieve this, it is crucial to understand the planning rules with two key objectives: (1) to verify if the constraints derived from the rules are verifiable on satellite images and (2) to use these constraints to guide the labelling (or semantization) of clusters. The first step in this process involves the automatic extraction of rules from urban planning documents written in the French language. To solve this problem, we propose a method based on the multilabel classification of textual segments and their subsequent summarization. This method includes a special format for representing segments, in which each segment has a title and a subtitle. We then propose a cascade approach to address the hierarchy of class labels. Additionally, we develop several text augmentation techniques for French texts that can improve prediction results. Finally, we reformulate classified segments into concise text portions containing necessary elements for expert rule construction. We adapt an approach based on Meaning Representation (AMR) graphs to generate these portions in the French language and conduct a comparative analysis with ChatGPT. We experimentally demonstrate that the resulting framework correctly classifies each type of segment with more than 90% accuracy. Furthermore, our results indicate that ChatGPT outperforms the AMR-based approach, leading to a discussion of the advantages and limitations of both methods.

Interpretation of geotechnical risk maps for Malatya province in terms of earthquake sequence on February 6, 2023

The earthquake sequence that occurred on February 6, 2023, centered in Türkiye caused extensive loss of life and significant damage. In this study, the geotechnical properties of the central districts of Malatya province, one of the provinces affected by these earthquakes, were calculated using data obtained. In the calculations, the correlations suggested by the Turkish Building Earthquake Code (TBEC) and internationally recommended correlations were used. Thus, the difference between the methods proposed by TBEC and internationally recommended correlations was interpreted. Using 1890 drilling data, 1765 seismic data, and 1764 microtremor data, calculations were made to determine bearing capacity values for 3 m x 3 m pad foundation, liquefaction potentials of the soil and soil classifications around this region. The results obtained from the calculations were mapped with geographical information systems-based software. Results of the study revealed that 2.9% of the study area in Battalgazi district and 1.71% for Yeşilyurt district had liquefaction potential. Almost 80% of each district was found to have a soil class of ZD (medium dense gravel and sand or clay layers) according to TBEC. The findings of the study were compared with previous studies, satellite images of the study area and post-earthquake observations. In areas where damage caused by the earthquake sequence was observed intensively, bearing capacity values were relatively low. It was concluded that building on poor soil conditions poses a profoundly serious risk in terms of earthquakes and very serious precautions should be taken by gathering several disciplines during the construction of these structures.

Band Weight-Optimized BiGRU Model for Large-Area Bathymetry Inversion Using Satellite Images

Currently, using satellite images combined with deep learning models has become an efficient approach for bathymetry inversion. However, only limited bands are usually used for bathymetry inversion in most methods, and they rarely applied for large-area bathymetry inversion (it is important for methods to be used in operational environments). Aiming to utilize all band information of satellite optical image data, this paper first proposes the Band Weight-Optimized Bidirectional Gated Recurrent Unit (BWO_BiGRU) model for bathymetry inversion. To further improve the accuracy, the Stumpf model is incorporated into the BWO_BiGRU model to form another new model—Band Weight-Optimized and Stumpf’s Bidirectional Gated Recurrent Unit (BWOS_BiGRU). In addition, using RANSAC to accurately extract in situ water depth points from the ICESat-2 dataset can accelerate computation speed and improve convergence efficiency compared to DBSCAN. This study was conducted in the eastern bay of Shark Bay, Australia, covering an extensive shallow-water area of 1725 km2. A series of experiments were performed using Stumpf, Band-Optimized Bidirectional LSTM (BoBiLSTM), BWO_BiGRU, and BWOS_BiGRU models to infer bathymetry from EnMAP, Sentinel-2, and Landsat 9 satellite images. The results show that when using EnMAP hyperspectral images, the bathymetry inversion of BWO_BiGRU and BWOS_BiGRU models outperform Stumpf and BoBiLSTM models, with RMSEs of 0.64 m and 0.63 m, respectively. Additionally, the BWOS_BiGRU model is particularly effective in nearshore water areas (depth between 0 and 5 m) of multispectral images. In general, comparing to multispectral satellite images, using the proposed BWO_BiGRU model to infer hyperspectral satellite images can achieve better bathymetry inversion results for large-area bathymetry maps.

LANDSCAPE FACTORS FORMING THE STEPPE ZONE OF THE ZHAYIK RIVER BASIN OF THE WEST KAZAKHSTAN REGION

This article examines the influence of various natural factors on the formation of landscape and soil complexes in the Zhaiyk River basin. The key components considered in the study include soil types, topography, and natural landscapes. The analysis reveals that the soils of the region range from chestnut and chernozem to sod-podzolic and solonetz soils, which determine the characteristics of vegetation and agricultural potential. Soil complexes are largely shaped by topography, water regime, and climatic conditions. Based on cartographic data obtained from satellite imagery and digital terrain models, an analysis was conducted to assess the distribution of soils and their relationship with vegetation types, water bodies, and other natural features. The results of the study reveal important patterns in the distribution of soil types and assess their role in the region’s ecosystems, providing practical insights for land resource management, agriculture, and environmental conservation in the Zhaiyk River basin. Topography, in turn, affects water exchange and erosion processes, which significantly influence soil types and their distribution. Special attention is given to identifying the interrelationships between soils, topography, and vegetation, as well as the role of these factors in the formation of sustainable ecosystems. The findings confirm that the complex interaction of topographical and soil features influences the distribution of landscape zones, which is crucial for planning agricultural activities and nature conservation.

IMPACT OF THE ZHAIYK RIVER ON CASPIAN SEA LEVEL

The Caspian Sea is subject to multi-year, seasonal and short-period changes in level, especially due to the influence of anthropogenic and climatic factors. The conducted correlation and regression analysis of water level data of the river Zhaiyk river – Atyrau city and the Caspian Sea - Peshnoy Station showed a fairly high linear relationship (r=0,93, R2 =0,87) between the long-term average daily values of characteristics for 2006...2023. Rise in the Zhaiyk river - Atyrau city in the period of low water is directly reflected in the sea level rise at the sea Peshnoy Station, which was clearly seen in the current year. Thus, space images of Sentinel-2 L2A satellite for April-May 2024 recorded the inflow of river water into the Caspian Sea. The assessment of the relationship between the characteristics under consideration showed that high correlations are not the main factor in determining the impact of the Zhaiyk river flow of the sea, for its northeastern part, other factors of level change (storm winds, tidal events and others) should be considered in particular.

Enhancing Operational Effectiveness in Security and Defence within the UAE: The Strategic Role of Artificial Intelligence

Purpose: The purpose of the study was to examine operational effectiveness in security and defence within the UAE: The strategic role of artificial intelligence. Methodology: The study applied both Qualitative and quantitative approach. For the qualitative component of this research, a complete literature analysis will be done to investigate the current body of scholarship, studies, and policy papers pertaining to the deployment of artificial intelligence (AI) in security and defense within the United Arab Emirates (UAE). Thematic analysis will be used for a qualitative data analysis method. This study will also apply quantitative approach. Data was collected using structured questionnaires and a structured survey distributed to 50 professionals to stakeholders within the UAE's security and military industries to obtain quantitative data on different areas of AI acceptance, usage, obstacles, and perceived influence on operational performance. Statistical software like Excel and Python will be used to perform quantitative data analysis. Charts, graphs, and plots will be used to visually present the survey results. Findings: The statistical findings reveal a significant relationship between AI adoption and enhanced decision-making capabilities. A strong positive correlation (r = 0.78, p < 0.001) between AI usage and improved situational awareness underscores AI’s capacity to process real-time data effectively. In cybersecurity, the analysis identifies a moderate positive correlation (r = 0.64, p < 0.01) between AI implementation and threat mitigation success. The participants have consistently emphasized ability of AI for analysis of vast datasets in the real time ensuring more informed and quick decision. It aligns with the global trends where the defense organizations would leverage AI for interpretation of satellite imagery and prediction of threats. The advanced machine learning algorithms have been proven effective for detection of anomalies like unauthorized access and phishing attack attempts. The participants are praising the technologies for improving the operational efficiency and reducing the human risks. Unique Contribution to Theory, Practice and Policy: Study highlights existing theories where AI improves decision making through real time insights. However, it challenges the deterministic views for AI as the infallible further emphasizing need for the hybrid models which integrates with the human judgement. The defense organizations need to adopt for hybrid approach where the AI is supporting instead of replacing the human decision making. The training programs need to be designed for equipping personnel with skills for interpreting the AI outputs critically. With the growing adversarial of AI, the investment across counter AI technologies has been imperative. It includes development of systems which could neutralize and identify the AI driven cyberattacks and foster collaborations with the global cybersecurity experts for staying ahead in emerging threats. The strengthening of partnerships with the international defense organizations could also help the UAE for leveraging the cutting-edge counters for AI solutions while sharing the threat intelligence effectively.

Temperate forests of high conservation value are successfully identified by satellite and LiDAR data fusion

AbstractForest ecosystems will play a critical role in achieving policy targets for biodiversity and conservation, such as those set out in the EU Biodiversity strategy for 2030. However, practitioners need to know where forests of high conservation value are to make the best‐informed decisions about which forests to prioritize. Here, we combine airborne LiDAR (airborne laser scanning/ALS), optical satellite imagery, and gridded datasets on soil and water availability with machine learning models to predict forests' conservation value across Denmark. We then use change‐detection algorithms to identify forests that had been disturbed since the collection of the LiDAR data to produce up‐to‐date estimates for the year 2020. Our models reached a high predictive capacity (82% accuracy) and suggested that 1982 km2 (~31%) of Denmark's forests were of potential high conservation value. Our study demonstrates the utility of data fusion approaches to identify forest areas of high value for conservation at fine spatial resolutions (~10–100 m) and nationwide extents. However, uncertainties remain in our approach. Hence, our findings should be used to guide field‐based assessments to confirm the in situ conservation value of the forests. Only in combination with such in situ data will approaches like ours enable decision makers to better protect forest biodiversity.

GIS and remote sensing based assessment of West Rapti River channel migration in Nepal

Abrupt changes in climatic conditions trigger river channels to migrate laterally due to changes in surface water conditions. West Rapti River in the Terai, a flat geographic region of Nepal with high mountains and Chure Hill on the north, is highly susceptible to water-induced disasters. Geographical Information System and Remotely Sensed Imageries were used to analyze the spatio-temporal changes of West Rapti River between 1990 and 2023, to assess their impact within the approximately 53 km range of Deukhuri Valley (Dune Valley). Using freely available Landsat satellite imagery we extracted water surface features through the Normalized Difference Water Index and generated 27 cross-sections (CS) to track channel shift. Those cross-sections were generated in the gap of 2000 m using the River Bathymetry Toolkit (RBT) to assess the Sinuosity & Braiding Index of the river channel within the planform. This study found that river channels migrated laterally determined as significant shifts, notably 1.43 km towards the northeast within CS-23 and 0.72 km towards the south direction within CS-25 in the last 33 years. Nearly no shifting impact was observed from CS-12 to CS-17 showing embankment and mitigation efforts being effective within this range. The study shows the river is naturally multi-channeled and exhibits a braided pattern with sinuosity index values ranging from 1.02 to 1.38, indicating highly braided conditions during 2010 and 2015. The river channel was found to be driven by a high sediment deposit of about 15.35 Sq. km across the 53 km range. These results are crucial for formulating integrated river basin management plans in the West Rapti River basin laying the foundation for future research to explore sustainable river management practices in the future.

Insights from feature tracking of optical satellite data for studying rock glacier kinematics in the Northern Tien Shan

Rock glaciers are prevalent across the Tien Shan and exhibit complex, but poorly understood kinematics linked to climate and environmental fluctuations. This study employed a frequency domain cross-correlation method to investigate rock glacier velocities in the Northern Tien Shan. We compared different sources of satellite imagery, including 0.5m Pléiades, 3m Planet, 10m Sentinel-2 and 15m Landsat-8 data. Analysis of high-resolution Pléiades imagery in the Central Ile Alatau showed considerable spatial heterogeneity in flow. The highest median velocity of 0.65 m/yr was observed on Timofeyeva rock glacier, with an upper quartile value of 0.90 m/yr. Ordzhonikidze and Morennyi rock glaciers also exhibited high activity, with upper quartile values of 1.91 m/yr and 0.96 m/yr, respectively, despite considerably lower mean and median values than Timofeyeva. We observed bimodal velocity distributions on a number of rock glaciers, highlighting the limitations of using mean and median statistics for characterising rock glacier activity. Sentinel-2 data was capable of detecting kinematic patterns that closely reflected those identified by high-resolution Pléiades data. Velocities were derived from Sentinel-2 imagery for 672 rock glaciers across the Northern Tien Shan over a 7-year period (2016–2023). Many of the larger rock glaciers in the regional inventory exhibited active areas with velocities that exceeded 2 m per year. Topographic analysis in the Central Ile Alatau and visual inspection showed the fastest velocities to generally occur on lower, flatter areas near the rock glacier front. However, topography did not entirely explain the spatial flow heterogeneity. We interpret that these spatial patterns in activity are related to individual rock glacier’s internal structure.

A Learned Reduced-Rank Sharpening Method for Multiresolution Satellite Imagery

This paper implements an unsupervised single-image sharpening method for multispectral images, focusing on Sentinel-2 and Landsat 8 imagery. Our method combines traditional model-based methods with neural network optimization techniques. Our method solves the same optimization problem as traditional model-based methods while leveraging neural network optimization techniques through a customized U-Net architecture and specialized loss function. The key innovation lies in simultaneously optimizing a low-rank approximation of the target image and a linear transformation from the subspace to the sharpened image within an unsupervised training framework. Our method offers several distinct advantages: it requires no external training data beyond the image being processed, it provides fast training speeds through a compact, interpretable network model, and most importantly, it adapts to different input images without requiring extensive parameter tuning—a common limitation of traditional methods. The method was developed with a focus on sharpening Sentinel-2 imagery. The Copernicus Sentinel-2 satellite constellation captures images at three different spatial resolutions, 10, 20, and 60 m, and many applications benefit from a unified 10 m resolution. Still, the method’s effectiveness extends to other remote sensing tasks, achieving competitive results in both sharpening and multisensor fusion scenarios. It is evaluated using both real and simulated data, and its versatility is shown through successful applications to Sentinel-2 sharpening and Sentinel-2/Landsat 8 fusion. In comparison with leading methods, it is shown to give excellent results.

Rural-urban transformation shapes oasis agriculture in Morocco’s High Atlas Mountains

Traditional agricultural activities and rural livelihoods in Morocco’s High Atlas Mountains are rapidly changing. This is triggered by increasing rural-urban interactions and new livelihood opportunities in cities. A typical example is the oasis of Tizi N’Oucheg in the country’s High Atlas Mountains, which over centuries was largely self-sufficient in food grain and livestock production. Improved infrastructure and better connections to distant urban centers have caused declining livelihood reliance on agricultural activities and enhanced dependence on remittances and the tourism sector in the region. Based on the case of Tizi N’Oucheg, this study aims at assessing the socio-economic and ecological implications of rural-urban transformation for ancient oasis systems in Morocco. Surveys on agricultural practices, census, and meteorological data were combined with GIS (Geographical Information System) -based analyses to examine land use and cropping pattern changes of 625 fields from 1967 to 2022. For the GIS analyses, historical aerial images, multispectral satellite images, and drone-based surveys were used to generate manually classified agricultural fields and NDVI (Normalized Difference Vegetation Index) time series. Our results show a major decline in cultivated land from 13 ha to 6.8 ha over the past 50 years accompanied by an expansion of modern infrastructure since the 2000s. Land management has shifted from labor-intensive multiple cropping and natural fertilization to monocropping of barley for local livestock feeding and increased application of mineral fertilization. The challenging geography of the oasis increased the hardship of practicing traditional agriculture, and therefore largely determines the response of the community to rural-urban transformation. Our data also highlight the increased financial dependence of rural populations on urban centers and the demise of traditional, sustainable agriculture in Morocco’s High Atlas Mountains if policies on agricultural development are not adapted to rural circumstances.

Six Decades of Rural Landscape Transformation in Five Lebanese Villages

During the last six decades, Lebanon’s landscapes have undergone significant regime shifts whose causes are under-investigated. Using land cover maps from 1962 and satellite imagery from 2014 and 2023 in five randomly selected villages across Lebanon’s major agroecological zones (AEZs), we identified salient trends in the urbanization-driven transformation of land use and land cover (LULC). Household socio-economic characteristics and environmental pressures were analyzed as independent variables influencing land use decisions. Logistic regression (LR) was employed to assess the significance of these variables in shaping farmers’ choices to transition toward “perennialization”—namely fruit tree monocropping or protected agriculture. The LR results indicate that education reduced the likelihood of “perennialization” by 45% (p < 0.001). Farm size positively influenced “perennialization” (p < 0.01), suggesting that land availability encourages this agricultural practice. In contrast, water availability negatively affects “perennialization” (p < 0.01), though farmers may still opt to irrigate by purchasing water during shortages. Our findings underline the complex interplay of socio-economic and environmental dynamics and historical events in shaping Lebanon’s rural landscapes and they offer insights into similar transformations across the Middle East and North Africa (MENA) region.

Vegetable Fields Mapping in Northeast China Based on Phenological Features

Developing vegetable agriculture is crucial for ensuring a balanced dietary structure and promoting nutritional health. However, remote sensing extraction in open-field vegetable planting areas faces several challenges, such as the mixing of target crops with natural vegetation caused by differences in climate conditions and planting practices, which hinders the development of large-scale vegetable field mapping. This paper proposes a classification method based on vegetable phenological characteristics (VPC), which takes into account the spatiotemporal heterogeneity of vegetable cultivation in Northeast China. We used a two-step strategy. First, Sentinel-2 satellite images and land use data were utilized to identify the optimal time and key indicators for vegetable detection based on the phenological differences in crop growth. Second, spectral analysis was integrated with three machine learning classifiers, which leveraged phenological and spectral features extracted from satellite images to accurately identify vegetable-growing areas. This combined approach enabled the generation of a high-precision vegetable planting map. The research findings reveal a consistent year-by-year increase in the planting area of vegetables from 2019 to 2023. The overall accuracy (OA) of the results ranges from 0.81 to 0.93, with a Kappa coefficient of 0.83. Notably, this is the first 10 m resolution regional vegetable map in China, marking a significant advancement in economic vegetable crop mapping.

UNet-GCViT: a UNet-based framework with global context vision transformer blocks for building damage detection

ABSTRACT Natural and man-made disasters take place around the world and cause significant financial and human losses. An accurate and fast post-disaster building damage mapping could play a crucial role in rapid rescue planning and operations. Remote sensing satellite images are the main source of building damage map generation. Usually, both pre-disaster and post-disaster satellite images are used for the generation of building damage maps, which encounter some challenges such as registration errors, noise, and atmospheric conditions. This study proposed a new method for building damage detection based only on post images with the UNet architecture network and Global Context Vision Transformer blocks. The deep learning network proposed in this research is automatic without any further processing. The proposed method comprises four main steps: (1) pre-processing, (2) network training, (3) building damage map generation, and (4) accuracy assessment for the final damage map. This network is applied to three different natural and man-made disaster datasets. The first dataset is the post-satellite image of the 2023 Turkey earthquake, the second one is the post-satellite image of the 2021 Bata explosion and the last one is the post-satellite image of the 2011 haiti earthquake. Results of the final building damage map indicate that the proposed method is highly effective with OA above 96%, which is superior to the other deep learning methods.

Impacts of Mangrove Loss on Greenhouse Gas Emissions in the Niger Delta, Nigeria

The mangrove vegetation within the Niger Delta region of Nigeria is ravaged by anthropogenic practices including but not limited to rapid urbanization, aquaculture expansion and oil exploration which penultimately distorts the biodiversity of both the mangrove and marine environments, culminating in the loss of structural and functional integrity of these ecosystems, specifically their role in climate change regulation. The study aimed at assessing the changes in mangrove covers from 1987 to 2022 in the study area as well as examining the changes in GHGs emissions resulting from the mangrove changes. The methodology adopted a remote sensing-based research design utilizing satellite imagery to analyze temporal changes in mangrove cover and evaluated their association with climate variables such as CO2 emissions and LST of the study area. Each satellite image geo-referenced in ArcGIS 10.8 & LULC changes calculated using geometry module of ArcGIS 10.8. NDIR spectroscopy was used in examining the variation in GHGs emissions. The data obtained revealed mangrove reduction from 12,991 km2 in 1987 to 9,089km2 in 2022 resulting in the loss of 3,904.00 km2 of mangrove forest. The reduction resulted in increased CO₂ emissions from 370.70 ppm to 403.29 ppm between 1987 and 2022. These results illustrate a clear link between mangrove cover change and CO₂ emissions, highlighting the critical role mangroves play in regulating climate change. The study was able to show that significant losses in mangrove cover have been closely associated with increased CO₂ emissions, thus reflecting the vital role these ecosystems play in carbon sequestration which underscores the importance of preserving these vital ecosystems to mitigate local and global climate impacts.

Application of UAV Photogrammetry and Multispectral Image Analysis for Identifying Land Use and Vegetation Cover Succession in Former Mining Areas

Variations in vegetation indices derived from multispectral images and digital terrain models from satellite imagery have been successfully used for reclamation and hazard management in former mining areas. However, low spatial resolution and the lack of sufficiently detailed information on surface morphology have restricted such studies to large sites. This study investigates the application of small, unmanned aerial vehicles (UAVs) equipped with multispectral sensors for land cover classification and vegetation monitoring. The application of UAVs bridges the gap between large-scale satellite remote sensing techniques and terrestrial surveys. Photogrammetric terrain models and orthoimages (RGB and multispectral) obtained from repeated mapping flights between November 2023 and May 2024 were combined with an ALS-based reference terrain model for object-based image classification. The collected data enabled differentiation between natural forests and areas affected by former mining activities, as well as the identification of variations in vegetation density and growth rates on former mining areas. The results confirm that small UAVs provide a versatile and efficient platform for classifying and monitoring mining areas and forested landslides.

Optimizing Deep Learning Models for Climate-Related Natural Disaster Detection from UAV Images and Remote Sensing Data

This research study utilized artificial intelligence (AI) to detect natural disasters from aerial images. Flooding and desertification were two natural disasters taken into consideration. The Climate Change Dataset was created by compiling various open-access data sources. This dataset contains 6334 aerial images from UAV (unmanned aerial vehicles) images and satellite images. The Climate Change Dataset was then used to train Deep Learning (DL) models to identify natural disasters. Four different Machine Learning (ML) models were used: convolutional neural network (CNN), DenseNet201, VGG16, and ResNet50. These ML models were trained on our Climate Change Dataset so that their performance could be compared. DenseNet201 was chosen for optimization. All four ML models performed well. DenseNet201 and ResNet50 achieved the highest testing accuracies of 99.37% and 99.21%, respectively. This research project demonstrates the potential of AI to address environmental challenges, such as climate change-related natural disasters. This study’s approach is novel by creating a new dataset, optimizing an ML model, cross-validating, and presenting desertification as one of our natural disasters for DL detection. Three categories were used (Flooded, Desert, Neither). Our study relates to AI for Climate Change and Environmental Sustainability. Drone emergency response would be a practical application for our research project.

Effects of land use/land cover change on soil physicochemical properties and soil carbon stock in Kochore district, southern Ethiopia

Land use changes from year to year due to natural and human-made factors are a serious cause of the degradation of soil properties. Therefore, this study aimed to investigate the impact of land use land cover changes on selected soil physicochemical properties and soil organic carbon stocks in Kochore district, Southern Ethiopia. Satellite images (2000, 2010, and 2020) were used as sources of information for land use and land cover analysis using ArcGIS 10.3 and ERDAS Imagine 2014 software. Three land use types (cultivated, agroforestry, and grazing land) were identified through field surveys and satellite image analysis. Soil samples were collected at different depths (0–20 cm and 20–40 cm), and selected soil properties were analyzed. The results indicate that geospatial data of the land cover of agroforestry continuously increased and a decrease in grazing and cultivated in the given periods of 2000, 2010, and 2020, and soil properties revealed such as sand, bulk density, organic carbon, total nitrogen, pH, cation exchange capacity, and exchangeable bases were significantly (P < 0.001) affected by land use and soil depth. The highest content of OC (2.37), Av.P. (3.36), and TN (0.13) was observed on agroforestry land, and the lowest 1.43 and 0.08 was OC and TN respectively. The highest value of soil organic carbon stock (60.2 mg ha−1) was observed in AFL. The study suggests the deterioration of soil properties under cultivated and grazing land, emphasizing the importance of sustainable integrated soil fertility management to optimize and maintain favorable soil physicochemical properties.