Multivariate spatiotemporal windspeeds prognostics across parts of Pacific Ocean using the Gaidai risk assessment approach

Spatial Information Research, Год журнала: 2025, Номер 33(1)

Опубликована: Янв. 22, 2025

Язык: Английский

---

Towards a standardized, ground-based network of hyperspectral measurements: Combining time series from autonomous field spectrometers with Sentinel-2

Remote Sensing of Environment, Год журнала: 2024, Номер 303, С. 114013 - 114013

Опубликована: Янв. 25, 2024

Язык: Английский

---

Assessing cropping system dynamics over three decades: remote sensing and GIS insights in Murshidabad-Jiaganj Block

Environmental Monitoring and Assessment, Год журнала: 2025, Номер 197(2)

Опубликована: Янв. 11, 2025

Язык: Английский

---

Post-Fire Burned Area Detection Using Machine Learning and Burn Severity Classification with Spectral Indices in İzmir: A SHAP-Driven XAI Approach

Fire, Год журнала: 2025, Номер 8(4), С. 121 - 121

Опубликована: Март 21, 2025

This study was conducted to precisely map burned areas in fire-prone forest regions of İzmir and analyze the spatial distribution wildfires. Using Sentinel-2 satellite imagery, burn severity first classified using dNBR dNDVI indices. Subsequently, machine learning (ML) algorithms—RF, XGBoost, LightGBM, AdaBoost—were employed classify unburned areas. To enhance model performance, hyperparameter optimization applied, results were evaluated multiple accuracy metrics. found that RF achieved highest with an overall 98.0% a Kappa coefficient 0.960. In comparison, classification based solely on spectral indices resulted accuracies 86.6% (dNBR) 81.7% (dNDVI). A key contribution this is integration Explainable Artificial Intelligence (XAI) through SHapley Additive exPlanations (SHAP) analysis, which used interpret influence environmental variables area classification. SHAP analysis made decision processes transparent identified dNBR, dNDVI, SWIR/NIR bands as most influential variables. Furthermore, analyses confirmed variations reflectance across fire-affected are critical for accurate delineation, particularly heterogeneous landscapes. provides scientific framework post-fire ecosystem restoration, fire management, disaster strategies, offering decision-makers data-driven effective intervention strategies.

Язык: Английский

---

Mapping the evolution patterns of urbanization, ecosystem service supply–demand, and human well-being: A tree-like landscape perspective

Ecological Indicators, Год журнала: 2023, Номер 154, С. 110591 - 110591

Опубликована: Июль 3, 2023

Ecosystem services (ESs) are closely related to human well-being (HWB). Recently, urbanization has increased worldwide, which had a significant impact on the ecosystem service supply–demand (ESSD) and HWB. However, previous studies have primarily focused spatiotemporal pattern of ESSD HWB, while ignoring their evolutionary pathways, especially in karst areas. We aimed quantify optimal trade-offs under constraints nonlinear relationship between further constructing tree-like framework explore pathways urbanization, ESSD, HWB from landscape evolution perspective. used production possibility frontier (PPF) three ESSDs, generalized additive model (GAM) fit geographic tree (Geotree) construct structure levels, comprehensive (CESD), There is trade-off deficit carbon storage (CS) water yield (WY), but synergy WY surplus FS. Further, there CSs food supply (FS). The response CS not obvious, FS obvious. Based Geotree model, CESD, present strong coupling relationships, show characteristics clustering, stratified heterogeneity, evolution.

Язык: Английский

---

An optimization model for the energy management of the network of tanks in a drinking water distribution system

International Transactions in Operational Research, Год журнала: 2025, Номер unknown

Опубликована: Янв. 6, 2025

Abstract “L'eau c'est la vie” is a well‐known French expression for “water life,” which reflects the fact that water undoubtedly most vital resource in world. The main mission utility companies to convey and distribute of acceptable quality satisfy demand population at any time day. In recent years, achieving this has become very challenging these companies. Indeed, on one hand, rapid growth expansion urbanization have significantly increased water, while other natural phenomenon, such as drought, well impact climate changes are making it almost impossible distribution right amount where when needed. presence storage tanks network aimed alleviating pressure by storing distributing later response variability across network. management done based assignment three‐level set points, allows meet outflow from each tank, maintaining adequate flow rate through points define level valves enable inflow tank be switched or off. However, operating during different periods day may yield extremely high operational cost because opening some will induce running pumps maintain an We present optimization model managing drinking system minimizing total electricity involved. Computational experiments been conducted up three sets networks. results show our proposed can used reduce 38%, still being able tanks.

Язык: Английский

---

Detection of Crop Damage in Maize Using Red–Green–Blue Imagery and LiDAR Data Acquired Using an Unmanned Aerial Vehicle

Agronomy, Год журнала: 2025, Номер 15(1), С. 238 - 238

Опубликована: Янв. 18, 2025

Crop damage caused by wild animals, particularly boars (Sus scrofa), significantly impacts agricultural yields, especially in maize fields. This study evaluates two methods for assessing crop using UAV-acquired data: (1) a deep learning-based approach employing the Deepness plugin QGIS, utilizing high-resolution RGB imagery; and (2) method based on digital surface models (DSMs) derived from LiDAR data. Manual visual assessment, supported ground-truthing, served as reference validating these methods. was conducted 2023 field Central Poland, where UAV flights captured imagery Results indicated that DSM-based achieved higher accuracy (94.7%) sensitivity (69.9%) compared to learning (accuracy: 92.9%, sensitivity: 35.3%), which exhibited precision (92.2%) specificity (99.7%). The provided closer estimation of total damaged area (9.45% field) (10.50%), while underestimated (4.01%). Discrepancies arose differences how partially areas were classified; excluded zones, focusing fully areas. findings suggest are well-suited quantifying extensive damage, techniques detect only completely Combining could enhance efficiency assessments. Future studies should explore integrated approaches across diverse types patterns optimize animal evaluation.

Язык: Английский

---

Enhancing flood prediction through remote sensing, machine learning, and Google Earth Engine

Frontiers in Water, Год журнала: 2025, Номер 7

Опубликована: Март 18, 2025

Floods are the most common natural hazard, causing major economic losses and severely affecting people’s lives. Therefore, accurately identifying vulnerable areas is crucial for saving lives resources, particularly in regions with restricted access insufficient data. The aim of this study was to automate identification flood-prone within a data-scarce, mountainous watershed using remote sensing (RS) machine learning (ML) models. In study, we integrate Normalized Difference Flood Index (NDFI), Google Earth Engine generate flood inventory, which considered step susceptibility mapping. Seventeen determining factors, namely, elevation, slope, aspect, curvature, Stream Power (SPI), Topographic Wetness (TWI), Ruggedness (TRI), Position (TPI), distance from roads, rivers, stream density, rainfall, lithology, Vegetation (NDVI), land use, length slope (LS) factor, Convergence were used map vulnerability. This aimed assess predictive performance gradient boosting, AdaBoost, random forest. model evaluated area under curve (AUC). assessment results showed that forest (RF) achieved highest accuracy (1), followed by boosting ensemble (RF-GB) (0.96), (GB) (0.95), AdaBoost (AdaB) (0.83). Additionally, research employed Shapely Additive Explanations (SHAP) method, explain predictions determine contributing factor each model. introduces novel approach providing significant insights into mapping, offering potential pathways future practical applications. Overall, emphasizes need urban planning emergency preparedness build safer more resilient communities.

Язык: Английский

---

Estimating the risk of wildfires in the municipality of Rio Verde, Goiás State, Central Brazil

Revista Brasileira de Ciências Ambientais, Год журнала: 2025, Номер 60

Опубликована: Март 13, 2025

The damage caused by wildfires has major impacts each year, not only on the environment but also economy and public health. present study aimed at mapping fire risk in different areas of municipality Rio Verde, Central Brazilian state Goiás. A number factors that influence occurrence were considered this analysis, including orientation relief, slope, population density, proximity homes, road network, land cover use. analytical hierarchy process was used to determine appropriate weights for variables. index divided into five classes: water, low, moderate, high, very high risks. Class 4 (high risk) most frequently recorded within area, followed classes 3 (moderate 2 (low risk). Subsequently, heat spots remote sensing related indices, framing verified. Overall, 16.36% low (class 2), while 36.29% classified as moderate 3), 46.72% 4). These findings indicate provides an adequate effective parameter spatial assessment distribution events (controlled burns or wildfires) Verde.

Язык: Английский

---

Remote sensing and GIS techniques for investigating air pollution’s impact on major crop yields

Environment Development and Sustainability, Год журнала: 2025, Номер unknown

Опубликована: Март 24, 2025

Язык: Английский

---