Data driven pathway analysis and forecast of global warming and sea level rise

Scientific Reports, Год журнала: 2023, Номер 13(1)

Опубликована: Апрель 4, 2023

Climate change is a critical issue of our time, and its causes, pathways, forecasts remain topic broader discussion. In this paper, we present novel data driven pathway analysis framework to identify the key processes behind mean global temperature sea level rise, forecast magnitude their increase from 2100. Based on historical dynamic statistical modeling alone, have established causal pathways that connect increasing greenhouse gas emissions level, with intermediate links encompassing humidity, ice coverage, glacier mass, but not for sunspot numbers. Our results indicate if no action taken curb anthropogenic emissions, average would rise an estimated 3.28 °C (2.46-4.10 °C) above pre-industrial while be 573 mm (474-671 mm) 2021 by However, countries adhere emission regulations outlined in United Nations Conference Change (COP26), lessen 1.88 (1.43-2.33 albeit still higher than targeted 1.5 °C, reduce 449 (389-509

Язык: Английский

---

A Machine Learning-Based Framework for Water Quality Index Estimation in the Southern Bug River

Water, Год журнала: 2023, Номер 15(20), С. 3543 - 3543

Опубликована: Окт. 11, 2023

River water quality is of utmost importance because the river not only one key resources but also a natural habitat serving its surrounding environment. In bid to address whether it has qualified quality, various analytics are required be considered, challenging measure all them frequently along reach. Therefore, estimating index (WQI) incorporating several weighted useful approach assess in rivers. This study explored applications ten machine learning (ML) models estimate WQI for Southern Bug River, which second-longest Ukraine. The ML methods considered this include artificial neural networks (ANNs), Support Vector Regressor (SVR), Extreme Learning Machine, Decision Tree Regressor, random forest, AdaBoost (AB), Gradient Boosting XGBoost (XGBR), Gaussian process (GP), and K-nearest neighbors (KNN). Each data measurement consists nine (NH4, BOD5, suspended solids, DO, NO3, NO2, SO4, PO4, Cl), while quantity more than 2700 points. results indicated that demonstrate satisfactory performance predicting WQI. However, GP outperformed other models, followed by XGBR, SVR, KNN. Furthermore, ANN AB demonstrated relatively weaker performance. Moreover, reliability assessment conducted on both training testing datasets confirmed comparative analysis. Overall, enhance assertion can sufficiently predict WQI, thereby enhancing management.

Язык: Английский

---

Improving PM2.5 prediction in New Delhi using a hybrid extreme learning machine coupled with snake optimization algorithm

Scientific Reports, Год журнала: 2023, Номер 13(1)

Опубликована: Ноя. 29, 2023

Fine particulate matter (PM2.5) is a significant air pollutant that drives the most chronic health problems and premature mortality in big metropolitans such as Delhi. In context, accurate prediction of PM2.5 concentration critical for raising public awareness, allowing sensitive populations to plan ahead, providing governments with information alerts. This study applies novel hybridization extreme learning machine (ELM) snake optimization algorithm called ELM-SO model forecast concentrations. The has been developed on quality inputs meteorological parameters. Furthermore, hybrid compared individual models, Support Vector Regression (SVR), Random Forest (RF), Extreme Learning Machines (ELM), Gradient Boosting Regressor (GBR), XGBoost, deep known Long Short-Term Memory networks (LSTM), forecasting results suggested exhibited highest level predictive performance among five testing value squared correlation coefficient (R2) 0.928, root mean square error 30.325 µg/m3. study's findings suggest technique valuable tool accurately concentrations could help advance field forecasting. By developing state-of-the-art pollution models incorporate ELM-SO, it may be possible understand better anticipate effects human environment.

Язык: Английский

---

Atmosphere air temperature forecasting using the honey badger optimization algorithm: on the warmest and coldest areas of the world

Engineering Applications of Computational Fluid Mechanics, Год журнала: 2023, Номер 17(1)

Опубликована: Фев. 24, 2023

Precisely forecasting air temperature as a significant meteorological parameter has critical role in environment quality management. Hence, this study employs hybrid intelligent model for accurately monthly one to three times ahead the hottest and coldest regions of world. The contains artificial neural network (ANN) hybridized with powerful hetaeristic Honey Badger Algorithm (HBA-ANN). average mutual information (AMI) technique is employed find optimal time delay values variable different horizons. Finally, performance developed compared classical ANN Gene Expression Programming (GEP) using some statistical criteria, Taylor scatter diagrams. Results indicated that each horizon, HBA-ANN lowest distance from observation points based on diagram, high NSE R2, low RMSE, MAE, RSR outperformed GEP models both training testing phases. could increase accuracy model. This model's precise supports case it be forecast other environmental parameters.

Язык: Английский

---

Improving multi-month hydrological drought forecasting in a tropical region using hybridized extreme learning machine model with Beluga Whale Optimization algorithm

Stochastic Environmental Research and Risk Assessment, Год журнала: 2023, Номер 37(12), С. 4963 - 4989

Опубликована: Сен. 9, 2023

Язык: Английский

---

Daily air temperature forecasting using LSTM-CNN and GRU-CNN models

Acta Geophysica, Год журнала: 2023, Номер 72(3), С. 2107 - 2126

Опубликована: Дек. 5, 2023

Язык: Английский

---

Machine learning models development for accurate multi-months ahead drought forecasting: Case study of the Great Lakes, North America

PLoS ONE, Год журнала: 2023, Номер 18(10), С. e0290891 - e0290891

Опубликована: Окт. 31, 2023

The Great Lakes are critical freshwater sources, supporting millions of people, agriculture, and ecosystems. However, climate change has worsened droughts, leading to significant economic social consequences. Accurate multi-month drought forecasting is, therefore, essential for effective water management mitigating these impacts. This study introduces the Multivariate Standardized Lake Water Level Index (MSWI), a modified index that utilizes level data collected from 1920 2020. Four hybrid models developed: Support Vector Regression with Beluga whale optimization (SVR-BWO), Random Forest (RF-BWO), Extreme Learning Machine (ELM-BWO), Regularized ELM (RELM-BWO). forecast droughts up six months ahead Superior Michigan-Huron. best-performing model is then selected remaining three lakes, which have not experienced severe in past 50 years. results show incorporating BWO improves accuracy all classical models, particularly turning points. Among RELM-BWO achieves highest accuracy, surpassing both by margin (7.21 76.74%). Furthermore, Monte-Carlo simulation employed analyze uncertainties ensure reliability forecasts. Accordingly, reliably forecasts lead time ranging 2 6 months. study's findings offer valuable insights policymakers, managers, other stakeholders better prepare mitigation strategies.

Язык: Английский

---

Deep learning versus hybrid regularized extreme learning machine for multi-month drought forecasting: A comparative study and trend analysis in tropical region

Heliyon, Год журнала: 2023, Номер 10(1), С. e22942 - e22942

Опубликована: Ноя. 28, 2023

Drought is a hazardous natural disaster that can negatively affect the environment, water resources, agriculture, and economy. Precise drought forecasting trend assessment are essential for management to reduce detrimental effects of drought. However, some existing modeling techniques have limitations hinder precise forecasting, necessitating exploration suitable approaches. This study examines two models, Long Short-Term Memory (LSTM) hybrid model integrating regularized extreme learning machine Snake algorithm, forecast hydrological droughts one six months in advance. Using Multivariate Standardized Streamflow Index (MSSI) computed from 58 years streamflow data drier Malaysian stations, models were compared classical such as gradient boosting regression K-nearest validation purposes. The RELM-SO outperformed other month ahead at station S1, with lower root mean square error (RMSE = 0.1453), absolute (MAE 0.1164), higher Nash-Sutcliffe efficiency index (NSE 0.9012) Willmott (WI 0.9966). Similarly, S2, had 0.1211 MAE 0.0909), 0.8941 WI 0.9960), indicating improved accuracy comparable models. Due significant autocorrelation data, traditional statistical metrics may be inadequate selecting optimal model. Therefore, this introduced novel parameter evaluate model's effectiveness accurately capturing turning points data. Accordingly, significantly 19.32 % 21.52 when LSTM. Besides, reliability analysis showed was most accurate providing long-term forecasts. Additionally, innovative analysis, an effective method, used analyze trends. revealed October, November, December experienced occurrences than months. research advances assessment, valuable insights decision-making drought-prone regions.

Язык: Английский

---

Permeation Flux Prediction of Vacuum Membrane Distillation Using Hybrid Machine Learning Techniques

Membranes, Год журнала: 2023, Номер 13(12), С. 900 - 900

Опубликована: Дек. 5, 2023

Vacuum membrane distillation (VMD) has attracted increasing interest for various applications besides seawater desalination. Experimental testing of technologies such as VMD on a pilot or large scale can be laborious and costly. Machine learning techniques valuable tool predicting performance scales. In this work, novel hybrid model was developed based incorporating spotted hyena optimizer (SHO) with support vector machine (SVR) to predict the flux pressure in VMD. The SVR–SHO validated experimental data benchmarked against other tools artificial neural networks (ANNs), classical SVR, multiple linear regression (MLR). results show that predicted high accuracy correlation coefficient (R) 0.94. However, models showed lower prediction than R-values ranging from 0.801 0.902. Global sensitivity analysis applied interpret obtained result, revealing feed temperature most influential operating parameter flux, relative importance score 52.71 compared 17.69, 17.16, 14.44 flowrate, vacuum intensity, concentration, respectively.

Язык: Английский

---

Predictive Analytics of Air Temperature in Alaskan Permafrost Terrain Leveraging Two-Level Signal Decomposition and Deep Learning

Forecasting, Год журнала: 2024, Номер 6(1), С. 55 - 80

Опубликована: Янв. 9, 2024

Local weather forecasts in the Arctic outside of settlements are challenging due to dearth ground-level observation stations and high computational costs. During winter, these critical help prepare for potentially hazardous conditions, while spring, may be used determine flood risk during annual snow melt. To this end, a hybrid VMD-WT-InceptionTime model is proposed multi-horizon multivariate forecasting remote-region temperatures Alaska over short-term horizons (the next seven days). First, Spearman correlation coefficient employed analyze relationship between each input variable forecast target temperature. The most output-correlated sequences decomposed using variational mode decomposition (VMD) and, ultimately, wavelet transform (WT) extract time-frequency patterns intrinsic raw inputs. resulting fed into deep InceptionTime forecasting. This technique has been developed evaluated 35+ years data from three locations Alaska. Different experiments performance benchmarks conducted learning models (e.g., Time Series Transformers, LSTM, MiniRocket), statistical conventional machine baselines GBDT, SVR, ARIMA). All performances assessed four metrics: root mean squared error, absolute percentage determination, directional accuracy. Superior achieved consistently technique.

Язык: Английский

---