☆ 4.7 Article

Deciphering the black box of deep learning for multi-purpose dam operation modeling via explainable scenarios

JOURNAL OF HYDROLOGY (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Multidisciplinary Sciences

Assessing the impacts of dam/weir operation on streamflow predictions using LSTM across South Korea

Yongsung Kwon et al.

Summary: Recently, weather data have been used in the LSTM model to predict streamflow, but this may not work well in regions with artificial water management structures. This study evaluated the accuracy of LSTM for streamflow prediction using dam/weir operational data in South Korea. Four scenarios were prepared, and the performance was assessed using NSE and RMSE. The results showed that adding dam/weir operational data improved the model's performance, especially when the structures had high frequency and large water discharge.

SCIENTIFIC REPORTS (2023)

添加到收藏夹

Article Meteorology & Atmospheric Sciences

Sub-Seasonal Experiment (SubX) Model-based Assessment of the Prediction Skill of Recent Multi-Year South Korea Droughts

Chang-Kyun Park et al.

Summary: Reliable sub-seasonal precipitation forecast is crucial for managing multi-year droughts in a timely manner. This study assessed the prediction skill of five Sub-seasonal Experiment (SubX) models for precipitation during recent multi-year South Korea droughts using various verification metrics. The results indicate that the prediction skill of the SubX models varied depending on the stage, event, and model during the droughts. The EMC-GEFSv12 model with 11 ensemble members showed the highest forecasting skill.

ASIA-PACIFIC JOURNAL OF ATMOSPHERIC SCIENCES (2023)

添加到收藏夹

Article Automation & Control Systems

On the possible benefits of deep learning for spectral preprocessing

Runar Helin et al.

Summary: Preprocessing is a crucial step in spectroscopy and spectrometry. This study aimed to explore the potential of using deep learning-based methods for spectral preprocessing. The results showed that deep learning-based preprocessing improved predictive performance, but classical preprocessing may still be a better alternative in some cases. However, using deep learning-based preprocessing with linear model prediction requires more effort and may not significantly enhance prediction performance compared to classical preprocessing.

JOURNAL OF CHEMOMETRICS (2022)

添加到收藏夹

Article Meteorology & Atmospheric Sciences

Large-Scale Sea Surface Temperature Forcing Contributed to the 2013-17 Record-Breaking Meteorological Drought in the Korean Peninsula

Yoo-Geun Ham et al.

Summary: This study examined the contribution of the Pacific decadal oscillation (PDO) to the record-breaking drought in the Korean Peninsula from 2013 to 2017. The study found that the positive phase of the PDO during the mid-2010s led to a precipitation deficit, resulting in 5 years of meteorological drought. The enhanced atmospheric heating anomalies over the Pacific, caused by PDO-related sea surface temperature warming, played a key role in reducing precipitation over the Korean Peninsula.

JOURNAL OF CLIMATE (2022)

添加到收藏夹

Article Engineering, Civil

Assessing the characteristics of recent drought events in South Korea using WRF-Hydro

Jaehyeong Lee et al.

Summary: This study demonstrates the characteristics of recent droughts in South Korea from 2008 to 2015 using the WRF-Hydro model. It shows that hydrological and agricultural droughts have a delayed response compared to meteorological droughts, and hydrological droughts are less severe than meteorological droughts due to attenuation propagation.

JOURNAL OF HYDROLOGY (2022)

添加到收藏夹

Article Engineering, Civil

Research on particle swarm optimization in LSTM neural networks for rainfall-runoff simulation

Yuanhao Xu et al.

Summary: This study proposes a deep learning neural network model based on LSTM networks and particle swarm optimization (PSO) to improve flood forecast accuracy and lead time. The model outperforms other models at different stations in the watersheds and is particularly effective for flood forecasting with lead times exceeding 6 hours.

JOURNAL OF HYDROLOGY (2022)

添加到收藏夹

Article Multidisciplinary Sciences

Breaking into the black box of artificial intelligence

Neil Savage

NATURE (2022)

添加到收藏夹

Article Engineering, Civil

Can Autonomous Vehicles Save Fuel? Findings from Field Experiments

Licheng Zhang et al.

Summary: This study compares the differences in speed control between autonomous vehicles and human-driven vehicles, highlighting the more effective speed control of autonomous vehicles. The experimental results show that fuel consumption of autonomous vehicles increases linearly with speed fluctuations.

JOURNAL OF ADVANCED TRANSPORTATION (2022)

添加到收藏夹

Article Environmental Sciences

Interpretation of ensemble learning to predict water quality using explainable artificial intelligence

Jungsu Park et al.

Summary: This study developed an XGBoost ensemble machine learning model to predict chlorophyll-a (Chl-a) concentration and explored the effect of input variable selection on model performance. Using explainable artificial intelligence (XAI) algorithms, the study provided interpretable analyses of model predictions. The results showed that selecting input variables based on the Shapley value (SHAP) algorithm improved model stability and helped reduce the cost of water quality analysis.

SCIENCE OF THE TOTAL ENVIRONMENT (2022)

添加到收藏夹

Article Computer Science, Information Systems

Real-Time Flood Monitoring with Computer Vision through Edge Computing-Based Internet of Things

Obaid Rafiq Jan et al.

Summary: This paper proposes a system architecture for water level monitoring using RGB-D cameras, which can monitor flood situations in open environments in real time. Data processing and water level information extraction are performed entirely on an edge computing device, greatly reducing the amount of data transmitted to the cloud server.

FUTURE INTERNET (2022)

添加到收藏夹

Article Engineering, Civil

A self-calibrating effective drought index (scEDI): Evaluation against social drought impact records over the Korean Peninsula (1777–2020)

Chang-Kyun Park et al.

JOURNAL OF HYDROLOGY (2022)

添加到收藏夹

Article Veterinary Sciences

Diel and monthly activity pattern of brown bears and sika deer in the Shiretoko Peninsula, Hokkaido, Japan

Kei Kawamura et al.

Summary: This study investigated the species distributions and activity patterns of terrestrial mammals, particularly brown bears and sika deer, on the Shiretoko Peninsula in Hokkaido, Japan, using camera-trap surveys. The diel activity pattern of brown bears was found to be diurnal/crepuscular, similar to bears in North America but different from European populations. The activity patterns of sika deer were crepuscular, with adult males more frequently observed during the autumn copulation period.

JOURNAL OF VETERINARY MEDICAL SCIENCE (2022)

添加到收藏夹

Article Geosciences, Multidisciplinary

Coupling a large-scale hydrological model (CWatM v1.1) with a high-resolution groundwater flow model (MODFLOW 6) to assess the impact of irrigation at regional scale

Luca Guillaumot et al.

Summary: Large-scale hydrological models are crucial for understanding and projecting future water resources. However, evaluating the accuracy of these models remains challenging due to coarse spatial resolution, simplified geological structures, and inadequate consideration of local water management practices.

GEOSCIENTIFIC MODEL DEVELOPMENT (2022)

添加到收藏夹

Article Geosciences, Multidisciplinary

Toward hyper-resolution global hydrological models including human activities: application to Kyushu island, Japan

Naota Hanasaki et al.

Summary: Global hydrological models that include human activities are powerful tools for assessing water availability and use at global and continental scales. The study applied different methods to Kyushu island in Japan and found that the localized model can provide more accurate estimation of water resources.

HYDROLOGY AND EARTH SYSTEM SCIENCES (2022)

添加到收藏夹

Article Engineering, Civil

Urban flood modeling using deep-learning approaches in Seoul, South Korea

Xinxiang Lei et al.

Summary: This study evaluated the capability of convolutional neural network (NNETC) and recurrent neural network (NNETR) models for flood hazard mapping in urban areas. The NNETC model showed slightly better prediction performance than the NNETR model, with terrain ruggedness index identified as the most important predictor.

JOURNAL OF HYDROLOGY (2021)

添加到收藏夹

Article Engineering, Civil

Assessing the new Natural Resources Conservation Service water supply forecast model for the American West: A challenging test of explainable, automated, ensemble artificial intelligence

Sean W. Fleming et al.

Summary: The M-4 ensemble artificial intelligence prototype shows superior performance in a wide range of tests, surpassing current benchmarks, and has been confirmed to meet NRCS requirements for operational adoption. This indicates that well-designed novel AI systems have the potential to transition into large-scale practical applications, with M-4 potentially being the largest AI migration into operational river forecasting to date.

JOURNAL OF HYDROLOGY (2021)

添加到收藏夹

Article Environmental Sciences

Long lead time drought forecasting using lagged climate variables and a stacked long short-term memory model

Abhirup Dikshit et al.

Summary: The study utilized a stacked long short-term memory (LSTM) model based on deep learning techniques for drought forecasting, demonstrating its effectiveness in predicting drought in both short-term and long-term lead times in the New South Wales region of Australia. Analysis of drought characteristics improved the understanding of drought forecasting, with statistical metrics used to evaluate model performance. Findings suggest potential for further testing of the architecture's forecasting capability at shorter temporal scales, providing valuable insights for government agencies.

SCIENCE OF THE TOTAL ENVIRONMENT (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

The effect of calibration data length on the performance of a conceptual hydrological model versus LSTM and GRU: A case study for six basins from the CAMELS dataset

Georgy Ayzel et al.

Summary: The study systematically compared the performance of the GR4H hydrological model with the LSTM and GRU neural networks in relation to the length of calibration data, revealing significant differences in model performance and convergence speed.

COMPUTERS & GEOSCIENCES (2021)

添加到收藏夹

Article Engineering, Civil

Can artificial intelligence and data-driven machine learning models match or even replace process-driven hydrologic models for streamflow simulation?: A case study of four watersheds with different hydro-climatic regions across the CONUS

Taereem Kim et al.

Summary: This study compared the classical PHMs and new DMLs in simulating rainfall-runoff relationship in watersheds, showing that DMLs perform well with delayed input scenarios, especially the ANN model. PHMs excel in low-flow regime, while DMLs are better in high-flow regime, indicating both have their strengths and are worthy of joint development.

JOURNAL OF HYDROLOGY (2021)

添加到收藏夹

Article Environmental Sciences

Direct Integration of Numerous Dams and Reservoirs Outflow in Continental Scale Hydrologic Modeling

Ahmad A. Tavakoly et al.

Summary: This study quantified the impact of dam regulations on streamflow and flood inundation by directly inserting operational daily flow release data at 175 dam locations into a streamflow simulation in the Mississippi River Basin. The inclusion of reservoir releases substantially improved the performance of the streamflow model, especially in the drier western region.

WATER RESOURCES RESEARCH (2021)

添加到收藏夹

Article Geosciences, Multidisciplinary

GMD perspective: The quest to improve the evaluation of groundwater representation in continental- to global-scale models

Tom Gleeson et al.

Summary: The article emphasizes the importance of continued modeling at both large-scale and regional-scale levels when it comes to groundwater models. It discusses evaluation methods for large-scale groundwater models, suggesting a combination of observation-based, model-based, and expert-based approaches. The article also encourages greater communication and cooperation among global hydrology and land surface modelers, local to regional hydrogeologists, and hydrologists focused on model development and evaluation to improve the representation of groundwater in large-scale models.

GEOSCIENTIFIC MODEL DEVELOPMENT (2021)

添加到收藏夹

Article Green & Sustainable Science & Technology

Diversity in the observed functionality of dams and reservoirs

Jonghun Kam

Summary: This study examines the functionality of dams and reservoirs globally, finding that factors such as human disturbance can impact the residence time of water in dams, affecting regional hydrological regimes. The study suggests that the magnitude of potential changes in residence time can be used as an indicator to identify the impact of dams and reservoirs on hydrological systems.

ENVIRONMENTAL RESEARCH: INFRASTRUCTURE AND SUSTAINABILITY (2021)

添加到收藏夹

Article Engineering, Civil

Exploring a Long Short-Term Memory based Encoder-Decoder framework for multi-step-ahead flood forecasting

I-Feng Kao et al.

JOURNAL OF HYDROLOGY (2020)

添加到收藏夹

Article Meteorology & Atmospheric Sciences

Extreme Precipitation Events in Northern California during Winter 2016-17: Multiscale Analysis and Climatological Perspective

Benjamin J. Moore et al.

MONTHLY WEATHER REVIEW (2020)

添加到收藏夹

Article Engineering, Civil

Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation

Shuai Gao et al.

JOURNAL OF HYDROLOGY (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

From local explanations to global understanding with explainable AI for trees

Scott M. Lundberg et al.

NATURE MACHINE INTELLIGENCE (2020)

添加到收藏夹

Article Energy & Fuels

A hybrid short-term load forecasting model based on variational mode decomposition and long short-term memory networks considering relevant factors with Bayesian optimization algorithm

Feifei He et al.

APPLIED ENERGY (2019)

添加到收藏夹

Article Environmental Sciences

Evaluation and machine learning improvement of global hydrological model-based flood simulations

Tao Yang et al.

ENVIRONMENTAL RESEARCH LETTERS (2019)

添加到收藏夹

Article Engineering, Civil

Real-time reservoir operation using recurrent neural networks and inflow forecast from a distributed hydrological model

Shuyu Yang et al.

JOURNAL OF HYDROLOGY (2019)

添加到收藏夹

Editorial Material Robotics

XAI-Explainable artificial intelligence

David Gunning et al.

SCIENCE ROBOTICS (2019)

添加到收藏夹

Proceedings Paper Computer Science, Software Engineering

Explainability Scenarios: Towards Scenario-based XAI Design

Christine T. Wolf

PROCEEDINGS OF IUI 2019 (2019)

添加到收藏夹

Review Environmental Sciences

Review on applications of artificial intelligence methods for dam and reservoir-hydro-environment models

Mohammed Falah Allawi et al.

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH (2018)

添加到收藏夹

Article Engineering, Civil

Modeling and simulating of reservoir operation using the artificial neural network, support vector regression, deep learning algorithm

Di Zhang et al.

JOURNAL OF HYDROLOGY (2018)

添加到收藏夹

Review Environmental Sciences

Flood Prediction Using Machine Learning Models: Literature Review

Amir Mosavi et al.

WATER (2018)

添加到收藏夹

Article Geosciences, Multidisciplinary

Assessing the climate-scale variability of atmospheric rivers affecting western North America

Alexander Gershunov et al.

GEOPHYSICAL RESEARCH LETTERS (2017)

添加到收藏夹

Editorial Material Environmental Sciences

The future role of dams in the United States of America

Michelle Ho et al.

WATER RESOURCES RESEARCH (2017)

添加到收藏夹

Article Computer Science, Artificial Intelligence

LSTM: A Search Space Odyssey

Klaus Greff et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2017)

添加到收藏夹

Article Ecology

Impacts of water level rise on algal bloom prevention in the tributary of Three Gorges Reservoir, China

Daobin Ji et al.

ECOLOGICAL ENGINEERING (2017)

添加到收藏夹

Article Multidisciplinary Sciences

Can we open the black box of AI?

Davide Castelvecchi

NATURE (2016)

添加到收藏夹

Article Water Resources

National drought management framework for drought preparedness in Korea (lessons from the 2014-2015 drought)

Ilpyo Hong et al.

WATER POLICY (2016)

添加到收藏夹

Article Engineering, Civil

Daily water level forecasting using wavelet decomposition and artificial intelligence techniques

Youngmin Seo et al.

JOURNAL OF HYDROLOGY (2015)

添加到收藏夹

Article Engineering, Civil

Multi-time-step ahead daily and hourly intermittent reservoir inflow prediction by artificial intelligent techniques using lumped and distributed data

V. Jothiprakash et al.

JOURNAL OF HYDROLOGY (2012)

添加到收藏夹

Article Engineering, Civil

A wavelet neural network conjunction model for groundwater level forecasting

Jan Adamowski et al.

JOURNAL OF HYDROLOGY (2011)

添加到收藏夹

Article Environmental Sciences

Hyperresolution global land surface modeling: Meeting a grand challenge for monitoring Earth's terrestrial water

Eric F. Wood et al.

WATER RESOURCES RESEARCH (2011)

添加到收藏夹

Article Engineering, Civil

Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling

Hoshin V. Gupta et al.

JOURNAL OF HYDROLOGY (2009)

添加到收藏夹

Article Engineering, Civil

Fitting of hydrologic models: A close look at the Nash-Sutcliffe index

Sharad K. Jain et al.

JOURNAL OF HYDROLOGIC ENGINEERING (2008)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.