Estimating FAO Blaney-Criddle b-Factor Using Soft Computing Models

Article Geosciences, Multidisciplinary

Spatial modeling of snow avalanche susceptibility using hybrid and ensemble machine learning techniques

Huseyin Akay

Summary: This study conducted snow avalanche susceptibility maps using belief function values and implemented ensemble models for prediction. The AdaBoost M1 ensemble of RT model was found to perform the best.

CATENA (2021)

添加到收藏夹

Article Computer Science, Information Systems

A Novel Hybrid Method for Landslide Susceptibility Mapping-Based GeoDetector and Machine Learning Cluster: A Case of Xiaojin County, China

Wei Xie et al.

Summary: A hybrid method combining GeoDetector and machine learning cluster was developed to assess landslide susceptibility, with the SVM model performing the best in the machine learning cluster and selected as the assessment model. The method effectively evaluated landslide susceptibility.

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION (2021)

添加到收藏夹

Article Computer Science, Information Systems

Prediction of Potential and Actual Evapotranspiration Fluxes Using Six Meteorological Data-Based Approaches for a Range of Climate and Land Cover Types

Mirka Mobilia et al.

Summary: The study assesses the accuracy of six meteorological data-based models in predicting evapotranspiration losses at monthly scale by comparing modelled fluxes with observed ones. Results show that model performances vary depending on vegetation and climate characteristics, with the Advection-Aridity approach generally being the most accurate, especially without model calibration. However, the Granger and Gray approach is the most accurate after calibration but is not recommended in data scarcity scenarios due to its high sensitivity to the calibration process.

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION (2021)

添加到收藏夹

Article Agronomy

Forecasting evapotranspiration in different climates using ensembles of recurrent neural networks

Francesco Granata et al.

Summary: This study developed three Recurrent Neural Network-based models for short-term ahead actual evapotranspiration prediction using deep learning algorithms. The LSTM models were more accurate than NARX models under subtropical climatic conditions in South Florida, while NARX models generally provided more accurate results in the semi-arid climate of Central Nevada.

AGRICULTURAL WATER MANAGEMENT (2021)

添加到收藏夹

Article Geosciences, Multidisciplinary

Landslide hazard assessment based on Bayesian optimization-support vector machine in Nanping City, China

Wei Xie et al.

Summary: The study proposed a novel approach for landslide hazard assessment using support vector machine (SVM) and Bayesian optimization (BO) algorithm and achieved better accuracy compared to the traditional SVM model. Through multicollinearity diagnosis and model validation, the optimized SVM model showed higher accuracy in landslide assessment.

NATURAL HAZARDS (2021)

添加到收藏夹

Article Agronomy