Time series predictions in unmonitored sites: a survey of machine learning techniques in water resources DOI Creative Commons
Jared Willard, Charuleka Varadharajan, Xiaowei Jia

et al.

Environmental Data Science, Journal Year: 2025, Volume and Issue: 4

Published: Jan. 1, 2025

Abstract Prediction of dynamic environmental variables in unmonitored sites remains a long-standing challenge for water resources science. The majority the world’s freshwater have inadequate monitoring critical needed management. Yet, need to widespread predictions hydrological such as river flow and quality has become increasingly urgent due climate land use change over past decades, their associated impacts on resources. Modern machine learning methods outperform process-based empirical model counterparts hydrologic time series prediction with ability extract information from large, diverse data sets. We review relevant state-of-the art applications streamflow, quality, other discuss opportunities improve emerging incorporating watershed characteristics process knowledge into classical, deep learning, transfer methodologies. analysis here suggests most prior efforts been focused frameworks built many at daily scales United States, but that comparisons between different classes are few inadequate. identify several open questions include inputs site characteristics, mechanistic understanding spatial context, explainable AI techniques modern frameworks.

Language: Английский

XAIR: A Systematic Metareview of Explainable AI (XAI) Aligned to the Software Development Process DOI Creative Commons
Tobias Clement,

Nils Kemmerzell,

Mohamed Abdelaal

et al.

Machine Learning and Knowledge Extraction, Journal Year: 2023, Volume and Issue: 5(1), P. 78 - 108

Published: Jan. 11, 2023

Currently, explainability represents a major barrier that Artificial Intelligence (AI) is facing in regard to its practical implementation various application domains. To combat the lack of understanding AI-based systems, Explainable AI (XAI) aims make black-box models more transparent and comprehensible for humans. Fortunately, plenty XAI methods have been introduced tackle problem from different perspectives. However, due vast search space, it challenging ML practitioners data scientists start with development software optimally select most suitable methods. this challenge, we introduce XAIR, novel systematic metareview promising tools. XAIR differentiates itself existing reviews by aligning results five steps process, including requirement analysis, design, implementation, evaluation, deployment. Through mapping, aim create better individual developing foster creation real-world applications incorporate explainability. Finally, conclude highlighting new directions future research.

Language: Английский

Citations

60
Artificial intelligence for geoscience: Progress, challenges and perspectives DOI Creative Commons
Tianjie Zhao, Sheng Wang,

Chaojun Ouyang

et al.

The Innovation, Journal Year: 2024, Volume and Issue: 5(5), P. 100691 - 100691

Published: Aug. 23, 2024

Public summary•What does AI bring to geoscience? has been accelerating and deepening our understanding of Earth Systems in an unprecedented way, including the atmosphere, lithosphere, hydrosphere, cryosphere, biosphere, anthroposphere interactions between spheres.•What are noteworthy challenges As we embrace huge potential geoscience, several arise reliability interpretability, ethical issues, data security, high demand cost.•What is future The synergy traditional principles modern AI-driven techniques holds immense promise will shape trajectory geoscience upcoming years.AbstractThis paper explores evolution geoscientific inquiry, tracing progression from physics-based models data-driven approaches facilitated by significant advancements artificial intelligence (AI) collection techniques. Traditional models, which grounded physical numerical frameworks, provide robust explanations explicitly reconstructing underlying processes. However, their limitations comprehensively capturing Earth's complexities uncertainties pose optimization real-world applicability. In contrast, contemporary particularly those utilizing machine learning (ML) deep (DL), leverage extensive glean insights without requiring exhaustive theoretical knowledge. ML have shown addressing science-related questions. Nevertheless, such as scarcity, computational demands, privacy concerns, "black-box" nature hinder seamless integration into geoscience. methodologies hybrid presents alternative paradigm. These incorporate domain knowledge guide methodologies, demonstrate enhanced efficiency performance with reduced training requirements. This review provides a comprehensive overview research paradigms, emphasizing untapped opportunities at intersection advanced It examines major showcases advances large-scale discusses prospects that landscape outlines dynamic field ripe possibilities, poised unlock new understandings further advance exploration.Graphical abstract

Language: Английский

Citations

56
How Interpretable Machine Learning Can Benefit Process Understanding in the Geosciences DOI Creative Commons
Shijie Jiang, Lily‐belle Sweet,

Georgios Blougouras

et al.

Earth s Future, Journal Year: 2024, Volume and Issue: 12(7)

Published: July 1, 2024

Abstract Interpretable Machine Learning (IML) has rapidly advanced in recent years, offering new opportunities to improve our understanding of the complex Earth system. IML goes beyond conventional machine learning by not only making predictions but also seeking elucidate reasoning behind those predictions. The combination predictive power and enhanced transparency makes a promising approach for uncovering relationships data that may be overlooked traditional analysis. Despite its potential, broader implications field have yet fully appreciated. Meanwhile, rapid proliferation IML, still early stages, been accompanied instances careless application. In response these challenges, this paper focuses on how can effectively appropriately aid geoscientists advancing process understanding—areas are often underexplored more technical discussions IML. Specifically, we identify pragmatic application scenarios typical geoscientific studies, such as quantifying specific contexts, generating hypotheses about potential mechanisms, evaluating process‐based models. Moreover, present general practical workflow using address research questions. particular, several critical common pitfalls use lead misleading conclusions, propose corresponding good practices. Our goal is facilitate broader, careful thoughtful integration into science research, positioning it valuable tool capable enhancing current

Language: Английский

Citations

29
Reliable water quality prediction and parametric analysis using explainable AI models DOI Creative Commons
M. K. Nallakaruppan,

E. Gangadevi,

M. Lawanya Shri

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: March 29, 2024

Abstract The consumption of water constitutes the physical health most living species and hence management its purity quality is extremely essential as contaminated has to potential create adverse environmental consequences. This creates dire necessity measure, control monitor water. primary contaminant present in Total Dissolved Solids (TDS), which hard filter out. There are various substances apart from mere solids such potassium, sodium, chlorides, lead, nitrate, cadmium, arsenic other pollutants. proposed work aims provide automation estimation through Artificial Intelligence uses Explainable (XAI) for explanation significant parameters contributing towards potability impurities. XAI transparency justifiability a white-box model since Machine Learning (ML) black-box unable describe reasoning behind ML classification. models Logistic Regression, Support Vector (SVM), Gaussian Naive Bayes, Decision Tree (DT) Random Forest (RF) classify whether drinkable. representations force plot, test patch, summary dependency plot decision generated SHAPELY explainer explain features, prediction score, feature importance justification estimation. RF classifier selected yields optimum Accuracy F1-Score 0.9999, with Precision Re-call 0.9997 0.998 respectively. Thus, an exploratory analysis indicators associated their significance. emerging research at vision addressing future well.

Language: Английский

Citations

24
Research on Water Resource Modeling Based on Machine Learning Technologies DOI Open Access
Liu Ze,

Jingzhao Zhou,

Xiaoyang Yang

et al.

Water, Journal Year: 2024, Volume and Issue: 16(3), P. 472 - 472

Published: Jan. 31, 2024

Water resource modeling is an important means of studying the distribution, change, utilization, and management water resources. By establishing various models, resources can be quantitatively described predicted, providing a scientific basis for management, protection, planning. Traditional hydrological observation methods, often reliant on experience statistical are time-consuming labor-intensive, frequently resulting in predictions limited accuracy. However, machine learning technologies enhance efficiency sustainability by analyzing extensive hydrogeological data, thereby improving optimizing utilization allocation. This review investigates application predicting aspects, including precipitation, flood, runoff, soil moisture, evapotranspiration, groundwater level, quality. It provides detailed summary algorithms, examines their technical strengths weaknesses, discusses potential applications modeling. Finally, this paper anticipates future development trends to

Language: Английский

Citations

21
Explainable Artificial Intelligence for Sustainable Urban Water Systems Engineering DOI Creative Commons

Shofia Saghya Infant,

A.S. Vickram,

A. Saravanan

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104349 - 104349

Published: Feb. 1, 2025

Language: Английский

Citations

2
Daily Streamflow Forecasting in Mountainous Catchment Using XGBoost, LightGBM and CatBoost DOI Creative Commons
Robert Szczepanek

Hydrology, Journal Year: 2022, Volume and Issue: 9(12), P. 226 - 226

Published: Dec. 13, 2022

Streamflow forecasting in mountainous catchments is and will continue to be one of the important hydrological tasks. In recent years machine learning models are increasingly used for such forecasts. A direct comparison use three gradient boosting (XGBoost, LightGBM CatBoost) forecast daily streamflow catchment our main contribution. As predictors we precipitation, runoff at upstream gauge station two-day preceding observations. All algorithms simple implement Python, fast robust. Compared deep (like LSTM), they allow easy interpretation significance predictors. tested achieved Nash-Sutcliffe model efficiency (NSE) range 0.85–0.89 RMSE 6.8–7.8 m3s−1. minimum 12 training data series required a result. The XGBoost did not turn out best forecast, although it most popular model. Using default parameters, results were obtained with CatBoost. By optimizing hyperparameters, by LightGBM. differences between much smaller than within themselves when suboptimal hyperparameters used.

Language: Английский

Citations

68
Explainable artificial intelligence and interpretable machine learning for agricultural data analysis DOI Creative Commons
Masahiro Ryo

Artificial Intelligence in Agriculture, Journal Year: 2022, Volume and Issue: 6, P. 257 - 265

Published: Jan. 1, 2022

Artificial intelligence and machine learning have been increasingly applied for prediction in agricultural science. However, many models are typically black boxes, meaning we cannot explain what the learned from data reasons behind predictions. To address this issue, I introduce an emerging subdomain of artificial intelligence, explainable (XAI), associated toolkits, interpretable learning. This study demonstrates usefulness several methods by applying them to openly available dataset. The dataset includes no-tillage effect on crop yield relative conventional tillage soil, climate, management variables. Data analysis discovered that can increase maize where is <5000 kg/ha maximum temperature higher than 32°. These useful answer (i) which variables important regression/classification, (ii) variable interactions prediction, (iii) how their with response variable, (iv) underlying a predicted value certain instance, (v) whether different algorithms offer same these questions. argue goodness model fit overly evaluated performance measures current practice, while questions unanswered. XAI enhance trust explainability AI.

Language: Английский

Citations

65
Does institutional quality affect CO2 emissions? Evidence from explainable artificial intelligence models DOI
Nicolae Stef, Hakan Başağaoğlu, Debaditya Chakraborty

et al.

Energy Economics, Journal Year: 2023, Volume and Issue: 124, P. 106822 - 106822

Published: June 21, 2023

Language: Английский

Citations

37
Revolutionizing Groundwater Management with Hybrid AI Models: A Practical Review DOI Open Access
Mojtaba Zaresefat, Reza Derakhshani

Water, Journal Year: 2023, Volume and Issue: 15(9), P. 1750 - 1750

Published: May 2, 2023

Developing precise soft computing methods for groundwater management, which includes quality and quantity, is crucial improving water resources planning management. In the past 20 years, significant progress has been made in management using hybrid machine learning (ML) models as artificial intelligence (AI). Although various review articles have reported advances this field, existing literature must cover ML. This article aims to understand current state-of-the-art ML used achievements domain. It most cited employed from 2009 2022. summarises reviewed papers, highlighting their strengths weaknesses, performance criteria employed, highly identified. worth noting that accuracy was significantly enhanced, resulting a substantial improvement demonstrating robust outcome. Additionally, outlines recommendations future research directions enhance of including prediction related knowledge.

Language: Английский

Citations

33