Forest fire susceptibility mapping with sensitivity and uncertainty analysis using machine learning and deep learning algorithms

Advances in Space Research, Год журнала: 2023, Номер 72(2), С. 426 - 443

Опубликована: Март 21, 2023

Язык: Английский

---

Hybrid ensemble machine learning approaches for landslide susceptibility mapping using different sampling ratios at East Sikkim Himalayan, India

Advances in Space Research, Год журнала: 2021, Номер 68(7), С. 2819 - 2840

Опубликована: Май 26, 2021

Язык: Английский

---

Coupling geographic information system integrated fuzzy logic-analytical hierarchy process with global and machine learning based sensitivity analysis for agricultural suitability mapping

Agricultural Systems, Год журнала: 2021, Номер 196, С. 103343 - 103343

Опубликована: Дек. 8, 2021

Язык: Английский

---

An integrated approach of machine learning and remote sensing for evaluating landslide hazards and risk hotspots, NW Himalaya

Remote Sensing Applications Society and Environment, Год журнала: 2024, Номер 33, С. 101140 - 101140

Опубликована: Янв. 1, 2024

Язык: Английский

---

IoT Smart Devices Risk Assessment Model Using Fuzzy Logic and PSO

Computers, materials & continua/Computers, materials & continua (Print), Год журнала: 2024, Номер 78(2), С. 2245 - 2267

Опубликована: Янв. 1, 2024

Increasing Internet of Things (IoT) device connectivity makes botnet attacks more dangerous, carrying catastrophic hazards.As IoT botnets evolve, their dynamic and multifaceted nature hampers conventional detection methods.This paper proposes a risk assessment framework based on fuzzy logic Particle Swarm Optimization (PSO) to address the risks associated with botnets.Fuzzy addresses threat uncertainties ambiguities methodically.Fuzzy component settings are optimized using PSO improve accuracy.The methodology allows for complex thinking by transitioning from binary continuous assessment.Instead expert inputs, data-driven tunes rules membership functions.This study presents complete system.The helps security teams allocate resources categorizing threats as high, medium, or low severity.This shows how CICIoT2023 can assess cyber risks.Our research has implications beyond detection, it provides proactive approach management promotes development secure environments.

Язык: Английский

---

Comprehensive landslide prediction mapping using bivariate statistical models of Mizoram state of Northeast India

Journal of Spatial Science, Год журнала: 2024, Номер 69(3), С. 963 - 993

Опубликована: Апрель 15, 2024

Landslides in the state of Mizoram result damage to life and properties annually. The study focuses on landslide susceptibility zones by frequency ratio (FR), evidential belief function (EBF) index entropy (IOE) models. A total 1,486 points were used build a relationship between 16 factors occurrences. results reveal 14.44%, 19.64% 3.55% area as very high susceptible FR, EBF IOE models, respectively. AUC support adoption model land use planning decision-making processes enhance natural resource management mitigate risks Mizoram.

Язык: Английский

---

Selecting optimal conditioning parameters for landslide susceptibility: an experimental research on Aqabat Al-Sulbat, Saudi Arabia

Environmental Science and Pollution Research, Год журнала: 2021, Номер 29(3), С. 3743 - 3762

Опубликована: Авг. 13, 2021

Язык: Английский

---

The development of a road network flood risk detection model using optimised ensemble learning

Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 122, С. 106081 - 106081

Опубликована: Март 14, 2023

Язык: Английский

---

Enhancing landslide management with hyper-tuned machine learning and deep learning models: Predicting susceptibility and analyzing sensitivity and uncertainty

Frontiers in Ecology and Evolution, Год журнала: 2023, Номер 11

Опубликована: Март 8, 2023

Introduction Natural hazards such as landslides and floods have caused significant damage to properties, natural resources, human lives. The increased anthropogenic activities in weak geological areas led a rise the frequency of landslides, making landslide management an urgent task minimize negative impact. This study aimed use hyper-tuned machine learning deep algorithms predict susceptibility model (LSM) provide sensitivity uncertainty analysis Aqabat Al-Sulbat Asir region Saudi Arabia. Methods Random forest (RF) was used model, while neural network (DNN) model. models were using grid search technique, best hypertuned for predicting LSM. generated validated receiver operating characteristics (ROC), F1 F2 scores, gini value, precision recall curve. DNN based conducted analyze influence parameters landslide. Results showed that RF predicted 35.1–41.32 15.14–16.2 km 2 high very zones, respectively. area under curve (AUC) ROC LSM by achieved 0.96 AUC, 0.93 AUC. results rainfall had highest landslide, followed Topographic Wetness Index (TWI), curvature, slope, soil texture, lineament density. Discussion Road density geology map prediction. may be helpful authorities stakeholders proposing plans considering potential sensitive parameters.

Язык: Английский

---

Game-theoretic optimization of landslide susceptibility mapping: a comparative study between Bayesian-optimized basic neural network and new generation neural network models

Environmental Science and Pollution Research, Год журнала: 2024, Номер 31(20), С. 29811 - 29835

Опубликована: Апрель 9, 2024

Язык: Английский

---