Evaluating Performances of LSTM, SVM, GPR, and RF for Drought Prediction in Norway: A Wavelet Decomposition Approach on Regional Forecasting

Water, Год журнала: 2024, Номер 16(23), С. 3465 - 3465

Опубликована: Дек. 2, 2024

A serious natural disaster that poses a threat to people and their living spaces is drought, which difficult notice at first can quickly spread wide areas through subtle progression. Numerous methods are being explored identify, prevent, mitigate distinct metrics have been developed. In order contribute the research on measures be taken against Standard Precipitation Evaporation Index (SPEI), one of drought indices has developed accepted in recent years includes more comprehensive definition, was chosen this study. Machine learning deep algorithms, including support vector machine (SVM), random forest (RF), long short-term memory (LSTM), Gaussian process regression (GPR), were used model droughts six regions Norway: Bodø, Karasjok, Oslo, Tromsø, Trondheim, Vadsø. Four architectures employed for goal, as novel approach, models’ output enhanced by using discrete wavelet decomposition/transformation (WT). The outputs evaluated correlation coefficient (r), Nash–Sutcliffe efficiency (NSE), root mean square error (RMSE) performance evaluation criteria. When findings analyzed, GPR (W-GPR), acquired after WT, typically produced best results. Furthermore, it discovered that, out all recognized models, M04 had most effective structure. Consequently, successful outcomes obtained with W-SVM-M04 Bodø W-GPR-M04 Oslo region results across (r: 0.9983, NSE: 0.9966 RMSE:0.0539).

Язык: Английский

---

Half-day (daytime and nighttime) precipitation extremes in China: Changes and attribution from 1981 to 2022

Global and Planetary Change, Год журнала: 2025, Номер 245, С. 104696 - 104696

Опубликована: Янв. 5, 2025

Язык: Английский

---

Sustainable Migration and Depopulation: A Methodological Proposal From the Perspective of the SDGs

Sustainable Development, Год журнала: 2025, Номер unknown

Опубликована: Янв. 23, 2025

ABSTRACT Sustainable development requires orderly migratory flows that avoid the resulting socio‐economic tensions in countries of origin and destination. Issues such as climate, armed conflicts lack job stability encourage human displacement towards large cities, simultaneously generating problems densification at destination depopulation abandoned areas. In this study, we analyzed link between determinants quality life immigration, with aim identify factors need to be strengthened “emptied” territories and, way, achieve a reasonable distribution population. We use methodological advance random forest order correctly address complexity variability data. The study is limited Spain's 19 autonomous regions, which suffer from both overpopulation, covering broad period guarantees robustness results (2008–2021). There evidence importance labor market, health education settlement migrants. Decision‐makers strengthen these aspects under‐inhabited areas by directing financial resources enhancing their attractiveness. This will make it possible redirect exodus re‐establishing economic social whole.

Язык: Английский

---

Improved estimation of stomatal conductance by combining high-throughput plant phenotyping data and weather variables through machine learning

Agricultural Water Management, Год журнала: 2025, Номер 309, С. 109321 - 109321

Опубликована: Янв. 25, 2025

Язык: Английский

---

Evaluation of IMERG precipitation product in the investigation of drought events in the Kermanshah Province

Acta Geophysica, Год журнала: 2025, Номер unknown

Опубликована: Март 8, 2025

Язык: Английский

---

Evolutionary polynomial modeling for interpretable drought prediction and resilient resource management

Ecological Informatics, Год журнала: 2025, Номер unknown, С. 103217 - 103217

Опубликована: Июнь 1, 2025

Язык: Английский

---

Severity of natural calamities and crop yield prediction using hybrid deep learning model in Uttar Pradesh

World Water Policy, Год журнала: 2024, Номер 10(1), С. 244 - 279

Опубликована: Фев. 1, 2024

Abstract Crop yield prediction has gained major potential for global food production. Predicting crop yields based on specific parameters like soil, environment, crop, and water been an interesting research topic in recent decades. To accurately predict yields, measuring the severities of natural calamities including level is mainly required. However, existing studies failed to because various issues overfitting problems, difficulty training, inability handle large data, reduced learning capability. Thus, proposed study develops efficient mechanism predicting by analyzing several calamities. Here, input samples are initially pre‐processed remove unwanted noises using data normalization standardization. enhance performance prediction, computed Extreme Gradient Boosting (XGBoost) model Palmer Drought Severity Index (PDSI), Severe Hail (SHI), Storm (SSI). Also, hyperparameters XGBoost tuned utilizing Sheep Flock Optimization Algorithm (SFOA). Finally, predicted proposing a new one‐dimensional convolutional gated recurrent unit neural network (1D‐CGRU). The classifier predicts with error rates mean square (MSE) 0.4363, root (RMSE) 0.1904, normalized squared (NRMSE) 0.00101, absolute (MAE) 0.2437, R ‐squared ( 2 ) .2756. significant findings positively indicate that this can be applicable real‐time agricultural practices highly suitable quality predictions. it assist farmers farming businesses crops season when harvest plant attaining improved yields.

Язык: Английский

---

Integration of SPEI and machine learning for assessing the characteristics of drought in the middle ganga plain, an agro-climatic region of India

Environmental Science and Pollution Research, Год журнала: 2024, Номер 31(54), С. 63098 - 63119

Опубликована: Окт. 29, 2024

Язык: Английский

---

Identifying inter-seasonal drought characteristics using binary outcome panel data models

Geocarto International, Год журнала: 2023, Номер 38(1)

Опубликована: Фев. 8, 2023

This study mainly focuses on spatiotemporal and inter-seasonal meteorological drought characteristics. Random Effect Logistic Regression Model (RELRM) Conditional Fixed (CFELRM) are used to identify the characteristics of in selected stations. The log-likelihood Ratio Chi-Square (LRCST) Wald chi-square tests (WCTs) assess significance RELRM CFELRM. Hausman test (HT) is applied select appropriate model between For instance, HT suggests CFELRM as an spring-to-summer modelling. significant coefficient from indicates that increment moisture conditions spring season will decrease probability summer. odds ratio 0.1942 means 19.42% chance being a higher category. Similarly, summer-to-autumn using computed 0.0673 shows 6.73%

Язык: Английский

---

The regional characteristics of meteorological drought event and its multidimensional factors measurement by daily SPEI in Guangxi, China

Geomatics Natural Hazards and Risk, Год журнала: 2022, Номер 14(1), С. 117 - 142

Опубликована: Дек. 19, 2022

The frequent occurrence of extreme drought events in Guangxi has caused huge losses to human beings and economy the region for many years. For fine identification evolution characteristics, this study adopted objective method regional (OITREE) carry out comprehensive feature involving multidimensional elements such as intensity, duration area meteorological based on daily standardized precipitation evapotranspiration index (SPEI) data from 1979 2018a. By comparing characteristics identified by grid SPEI statistical analysis OITREE, a framework factor's measurement is formed study. Specifically, more convenient identify single point OITREE better at describing overall spatiotemporal events. found that flash droughts seasonal occurred alternately were superimposed concurrently Guangxi, spatial temporal these two types significantly different. In concrete terms, average annual frequency was 2.0–3.8, varied 20 60 d, concentration had region-wide dispersion; while 0.82–1.65, 40 105 local concentration. Furthermore, drought, total three-dimension clustering introduced realize intensity heterogeneity partition mapping Guangxi. research results can provide important scientific support promoting operational risk assessment regulation disasters forecasting warning.

Язык: Английский

---