Applied Computing and Geosciences最新文献

{"title":"Land use and land cover classification for change detection studies using convolutional neural network","authors":"V. Pushpalatha ,&nbsp;P.B. Mallikarjuna ,&nbsp;H.N. Mahendra ,&nbsp;S. Rama Subramoniam ,&nbsp;S. Mallikarjunaswamy","doi":"10.1016/j.acags.2025.100227","DOIUrl":"10.1016/j.acags.2025.100227","url":null,"abstract":"<div><div>Efficient land use land cover (LULC) classification is crucial for environmental monitoring, urban planning, and resource management. This study investigates LULC changes in Nanjangud taluk, Mysuru district, Karnataka, India, using remote sensing (RS) and geographic information systems (GIS). This paper mainly focuses on the classification and change detection analysis of LULC in 2010 and 2020 using linear imaging self-scanning sensor-III (LISS-III) remote sensing images. Traditional methods for LULC classification involve manual interpretation of satellite images, which provides lower accuracy. Therefore, this paper proposed the Convolutional Neural Network (CNN)-based deep learning method for LULC classification. The main objective of the research work is to perform an efficient LULC classification for the change detection study of the Nanjagud taluk using the classified maps of the years 2010 and 2020. The experimental results indicate that the proposed classification method is outperformed, with an overall accuracy of 94.08% for the 2010 data and 95.30% for the 2020 data. Further, change detection analysis has been carried out using classified maps and the results show that built-up areas increased by 8.34 sq. km (0.83%), agricultural land expanded by 2.21 sq. km (0.23%), and water bodies grew by 3.31 sq. km (0.35%). Conversely, forest cover declined by 1.49 sq. km (0.15%), and other land uses reduced by 11.93 sq. km (1.22%) over the decade.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"25 ","pages":"Article 100227"},"PeriodicalIF":2.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166134","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced AI techniques for landslide susceptibility mapping and spatial prediction: A case study in Medellín, Colombia","authors":"I.N. Gómez-Miranda ,&nbsp;C. Restrepo-Estrada ,&nbsp;A. Builes-Jaramillo ,&nbsp;João Porto de Albuquerque","doi":"10.1016/j.acags.2025.100226","DOIUrl":"10.1016/j.acags.2025.100226","url":null,"abstract":"<div><div>Landslides, a global phenomenon, significantly impact economies and societies, especially in densely populated areas. Effective mitigation requires awareness of landslide risks, yet temporal links between occurrences are often neglected, challenging model performance due to non-stationary triggering and predisposing factors. This study presents a novel landslide susceptibility model that incorporates spatial and temporal dependencies, including landslide recurrence. We applied AI models — Naive Bayes, Linear Discriminant Analysis, Quadratic Discriminant Analysis, Decision Trees, Random Forest, and Support Vector Machine (SVM) — to a case study in Medellín, a mountainous city in northwest Colombia. Using heuristic methods, we evaluated geological and geomorphological characteristics to identify high-risk areas. Integrating temporal data from four consecutive periods allowed us to enhance estimation robustness by incorporating random effects. Our findings identify slope, stream distance, geology, geomorphology, and mean annual precipitation as key factors influencing landslide susceptibility in Medellín. The SVM model demonstrated superior performance with an accuracy of 85%, closely aligning with previous studies. This research underscores the importance of temporal dynamics in landslide susceptibility assessments, improving prediction accuracy and supporting more effective risk management.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"25 ","pages":"Article 100226"},"PeriodicalIF":2.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143387194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pymaginverse: A python package for global geomagnetic field modeling","authors":"Frenk Out ,&nbsp;Maximilian Schanner ,&nbsp;Liz van Grinsven ,&nbsp;Monika Korte ,&nbsp;Lennart V. de Groot","doi":"10.1016/j.acags.2025.100222","DOIUrl":"10.1016/j.acags.2025.100222","url":null,"abstract":"<div><div>Data-based geomagnetic models are key for mapping the global field, predicting the movement of magnetic poles, understanding the complex processes happening in the outer core, and describing the global expression of magnetic field reversals. There exists a wide range of models, which differ in a priori assumptions and methods for spatio-temporal interpolation. A frequently used modeling procedure is based on regularized least squares (RLS) spherical harmonic analysis, which has been used since the 1980s. The first version of this algorithm has been written in Fortran and inspired many different research groups to produce versions of the algorithm in other programming languages, either published open-access or only accessible within the institute. To open up the research field and allow for reproducibility of results between existing versions, we provide a user-friendly open-source Python version of this popular algorithm. We complement this method with an overview on background literature – concerning Maxwells equations, spherical harmonics, cubic B-Splines, and regularization – that forms the basis for RLS geomagnetic models. We included six spatial and two temporal damping methods from literature to further smooth the magnetic field in space and time. Computational resources are kept to a minimum by employing the banded structure of the normal equations involved and incorporating C-code (with Cython) for matrix formation, enabling a massive speed-up. This ensures that the algorithm can be executed on a simple laptop, and is as fast as its Fortran predecessor. Four tutorials with ample examples show how to employ the new lightweight and quick algorithm. With this properly documented open-source Python algorithm, we have the intention to encourage current and new users to employ and further develop the method.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"25 ","pages":"Article 100222"},"PeriodicalIF":2.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143165476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic variogram inference using pre-trained Convolutional Neural Networks","authors":"Mokdad Karim ,&nbsp;Koushavand Behrang ,&nbsp;Boisvert Jeff","doi":"10.1016/j.acags.2025.100219","DOIUrl":"10.1016/j.acags.2025.100219","url":null,"abstract":"<div><div>A novel approach is presented for inferring covariance functions from sparse data using Convolutional Neural Networks (CNNs). Two workflows are proposed: (1) direct prediction of variogram model parameters, and (2) prediction of experimental variogram values at specified lag distances, which are smooth and easily autofit. Workflow 1 achieves an r-squared of 0.80, while Workflow 2 attains a higher r-squared of 0.96. Data augmentation through rotation improves robustness, and can be used to examine variogram uncertainty; the distribution for each predicted parameter can be obtained and used in uncertainty modeling. The CNNs are pre-trained, ensuring minimal computational time and fully automated processing. The workflows are applicable to sparse or dense data but are currently limited to 2D normal score variograms.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"25 ","pages":"Article 100219"},"PeriodicalIF":2.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143165477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Developing ground motion prediction models for West Java: A machine learning approach to support Indonesia's earthquake early warning system","authors":"Andy Rachmadan,&nbsp;Ardiansyah Koeshidayatullah,&nbsp;SanLinn I. Kaka","doi":"10.1016/j.acags.2024.100212","DOIUrl":"10.1016/j.acags.2024.100212","url":null,"abstract":"<div><div>Indonesia, one of the most earthquake-prone countries in the world, is currently developing an Earthquake Early Warning (EEW) system. A key component of this system, the Regional EEW, relies on Ground Motion Prediction models (GMPMs) to issue end-user alerts. However, in West Java, one of the pilot regions for this project, there is a lack of region-specific GMPMs essential for accurate early warnings. Traditionally, GMPMs are developed using linear regression based on complex, predefined mathematical equations and coefficients. However, Machine learning offers the advantages of bypassing the need for predefined equations and effectively capturing the nonlinear behavior present in ground motion data. To address this gap, we evaluated three machine learning algorithms (i.e. Artificial Neural Network [ANN], Gradient Boosting [GB], and Random Forest [RF]) to develop GMPMs for three tectonic categories: shallow-crustal, interface, and intraslab. These models were used to predict Peak Ground Acceleration (PGA) in West Java, utilizing 3116 strong ground motion records from 365 earthquakes with moment magnitude ranging from 2.4 to 7 and epicentral distance between 5.5 and 867 km, recorded since 2010. Our results show that The Gradient Boosting model outperformed the others across all three tectonic categories, with the lowest Mean Squared Error values (0.94, 0.60, 0.65), and Standard Deviation of Residuals (0.97, 0.77, 0.80), as well as the highest Pearson correlation coefficient-value (0.83, 0.88, 0.90) for shallow-crustal, interface, and intraslab events, respectively, demonstrating strong accuracy in predicting PGA. The model was further validated with recent earthquake data and from 2024 showing good agreement and confirming its robustness. Epicentral Distance and Moment Magnitude were the most influential in predicting PGA among the six explanatory variables used in this study. These findings highlight the potential of machine learning models to improve the accuracy of ground-shaking predictions, contributing to the success of Indonesia's Earthquake Early Warning System (EEWS).</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"25 ","pages":"Article 100212"},"PeriodicalIF":2.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deformation analysis by an improved similarity transformation","authors":"Vahid Mahboub","doi":"10.1016/j.acags.2025.100221","DOIUrl":"10.1016/j.acags.2025.100221","url":null,"abstract":"<div><div>In this contribution, deformation analysis is rigorously performed by a non-linear 3-D similarity transformation. In contrast to traditional methods based on linear least-squares (LLS), here we solve a non-linear problem without any linearization. To achieve this goal, a new weighted total least-squares (WTLS) approach with general dispersion matrix is implemented to deformation analysis problem. Although some researchers have been trying to solve deformation analysis using TLS approaches, these attempts require modification since they used to apply unstructured TLS techniques such as Generalized TLS (GTLS) to similarity transformation which requires structured TLS (STLS) techniques while the WTLS approach preserves the structure of the functional model when based on the perfect description of the variance-covariance matrix. As a secondary scope, here it is analytically proved that LLS is not identical to nonlinear estimations such as the WTLS methods and rigorous nonlinear least-square (RNLS) as opposed to what in some contributions has been claimed. The third attainment of this contribution is proposing another algorithm for rigorous similarity transformation with arbitrary rotational angles. It is based on the RNLS method which can obtain the correct update of misclosure. Moreover, compared to transformation methods that deal with arbitrary rotational angles, we do not need to impose any orthogonality constraints here. Two case studies numerically confirm that the WTLS and RNLS methods provide the most accurate results among the LLS, GTLS, RNLS and WTLS approaches in two landslide areas.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"25 ","pages":"Article 100221"},"PeriodicalIF":2.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143165022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Irrigated rice-field mapping in Brazil using phenological stage information and optical and microwave remote sensing","authors":"Andre Dalla Bernardina Garcia ,&nbsp;MD Samiul Islam ,&nbsp;Victor Hugo Rohden Prudente ,&nbsp;Ieda Del’Arco Sanches ,&nbsp;Irene Cheng","doi":"10.1016/j.acags.2025.100223","DOIUrl":"10.1016/j.acags.2025.100223","url":null,"abstract":"<div><div>Irrigated rice-field mapping methodologies have been rapidly evolving as a result of advanced remote sensing (RS) technology. However, current methods rely on extensive time-series data and a wide range of multi-spectral bands. These methods often struggle with classification accuracy with contaminated satellite data due to environmental factors or acquisition device constraints, e.g., cloud cover, shadows, noise, and the temporal and spectral resolution trade-off. Our goal is map irrigated rice-field by using a suitable satellite image band composition instead of time-series data. We divide the growth cycle into different rice phenological stages: beginning, middle and end of season, as well as the season transition periods. Near-infrared (NIR), short-wave infrared (SWIR) and red bands of MultiSpectral Instrument - MSI/Sentinel-2 (optical RS), along with polarizations of VV (vertical–vertical) and VH (vertical–horizontal) of Sentinel-1 C-band Synthetic Aperture Radar (SAR) (microwave RS), were used to create ten different false-color image composites. Ground truth maps from two consecutive growth seasons (2017/2018 and 2018/2019) served as references. We applied a modified version of the Fusion Adaptive Patch Network (FAPNET), named as Patch Layer Adaptive Network (PLANET) convolutional neural network (CNN) to obtain binary rice mapping, which was evaluated using the traditional Mean Intersection over Union (MIoU) and Dice coefficient. Analytic results show that the end of season is the most suitable for obtaining a reliable classification based on optical and SAR sensors. Although complex rice-field pose challenges, our predictions consistently scored a MIoU above 0.9. We conclude that choosing the right phenological stage for rice mapping combined with deep learning model can greatly improve the classification results. These results indicate that the choice of composition significantly impacts classification accuracy, especially in more complex environments.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"25 ","pages":"Article 100223"},"PeriodicalIF":2.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143165475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rapid mapping of landslides using satellite SAR imagery: A progressive learning approach","authors":"Nikhil Prakash ,&nbsp;Andrea Manconi ,&nbsp;Alessandro Cesare Mondini","doi":"10.1016/j.acags.2025.100224","DOIUrl":"10.1016/j.acags.2025.100224","url":null,"abstract":"<div><div>Rapid detection of landslides after an exceptional event is critical for planning effective disaster management. Previous works have typically used machine learning-based methods, including the recently popular deep-learning approaches, to identify characteristics surface features from satellite remote sensing data, especially from optical images. However, data acquisition from optical images is not possible in cloudy conditions, leading to unpredictable delays in any mapping task from future events. These methods also rely on large manually labelled inventories for training, which is often not available before the event. In this work, we propose an active training strategy to generate a landslide map after an event using the first available synthetic-aperture radar (SAR) image and improve it once subsequent cloud-free optical images are acquired. The proposed active learning workflow can start with a small (<span><math><mrow><mo>∼</mo><mn>100</mn><msup><mrow><mi>m</mi></mrow><mrow><mn>2</mn></mrow></msup></mrow></math></span>) and incomplete inventory,- and can grow the extent and completeness in iterative steps with manual updates after each step. This significantly reduces the slow manual mapping typically required for generating a large training inventory. We designed our experiments to map the landslides triggered by the <span><math><msub><mrow><mi>M</mi></mrow><mrow><mi>w</mi></mrow></msub></math></span> 6.6 Hokkaido Eastern Iburi earthquake of 2018 in Japan using sequentially ALOS-2 (SAR) and PlanetScope (Optical) scenes in the order they are acquired. The choice of active learning prioritizes speed over accuracy. However, we note only a modest reduction in performance (<span><math><mrow><mo>∼</mo><mn>10</mn><mtext>%</mtext></mrow></math></span> drop in F1 and MCC scores), with our method allowing a preliminary landslide inventory to be completed within a single day. This is of major importance in disaster response, improving performance and reducing the potential subjectivity associated with manual mapping.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"25 ","pages":"Article 100224"},"PeriodicalIF":2.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Do more with less: Exploring semi-supervised learning for geological image classification","authors":"Hisham I. Mamode,&nbsp;Gary J. Hampson,&nbsp;Cédric M. John","doi":"10.1016/j.acags.2024.100216","DOIUrl":"10.1016/j.acags.2024.100216","url":null,"abstract":"<div><div>Labelled datasets within geoscience can often be small, with data acquisition both costly and challenging, and their interpretation and downstream use in machine learning difficult due to data scarcity. Deep learning algorithms require large datasets to learn a robust relationship between the data and its label and avoid overfitting. To overcome the paucity of data, transfer learning has been employed in classification tasks. But an alternative exists: there often is a large corpus of unlabeled data which may enhance the learning process. To evaluate this potential for subsurface data, we compare a high-performance semi-supervised learning (SSL) algorithm (SimCLRv2) with supervised transfer learning on a Convolutional Neural Network (CNN) in geological image classification.</div><div>We tested the two approaches on a classification task of sediment disturbance from cores of International Ocean Drilling Program (IODP) Expeditions 383 and 385. Our results show that semi-supervised transfer learning can be an effective strategy to adopt, with SimCLRv2 capable of producing representations comparable to those of supervised transfer learning. However attempts to enhance the performance of semi-supervised transfer learning with task-specific unlabeled images during self-supervision degraded representations. Significantly, we demonstrate that SimCLRv2 trained on a dataset of core disturbance images can out-perform supervised transfer learning of a CNN once a critical number of task-specific unlabeled images are available for self-supervision. The gain in performance compared to supervised transfer learning is 1% and 3% for binary and multi-class classification, respectively.</div><div>Supervised transfer learning can be deployed with comparative ease, whereas the current SSL algorithms such as SimCLRv2 require more effort. We recommend that SSL be explored in cases when large amounts of unlabeled task-specific images exist and improvement of a few percent in metrics matter. When examining small, highly specialized datasets, without large amounts of unlabeled images, supervised transfer learning might be the best strategy to adopt. Overall, SSL is a promising approach and future work should explore this approach utilizing different dataset types, quantity, and quality.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"25 ","pages":"Article 100216"},"PeriodicalIF":2.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Semantic segmentation framework for atoll satellite imagery: An in-depth exploration using UNet variants and Segmentation Gym","authors":"Ray Wang ,&nbsp;Tahiya Chowdhury ,&nbsp;Alejandra C. Ortiz","doi":"10.1016/j.acags.2024.100217","DOIUrl":"10.1016/j.acags.2024.100217","url":null,"abstract":"<div><div>This paper presents a framework for semantic segmentation of satellite imagery aimed at studying atoll morphometrics. Recent advances in deep neural networks for automated segmentation have been valuable across a variety of satellite and aerial imagery applications, such as land cover classification, mineral characterization, and disaster impact assessment. However, identifying an appropriate segmentation approach for geoscience research remains challenging, often relying on trial-and-error experimentation for data preparation, model selection, and validation. Building on prior efforts to create reproducible research pipelines for aerial image segmentation, we propose a systematic framework for custom segmentation model development using Segmentation Gym, a software tool designed for efficient model experimentation. Additionally, we evaluate state-of-the-art U-Net model variants to identify the most accurate and precise model for specific segmentation tasks. Using a dataset of 288 Landsat images of atolls as a case study, we conduct a detailed analysis of various annotation techniques, image types, and training methods, offering a structured framework for practitioners to design and explore segmentation models. Furthermore, we address dataset imbalance, a common challenge in geographical data, and discuss strategies to mitigate its impact on segmentation outcomes. Based on our findings, we provide recommendations for applying this framework to other geoscience research areas to address similar challenges.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"25 ","pages":"Article 100217"},"PeriodicalIF":2.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}