Predicting Changes in Spatiotemporal Groundwater Storage Through the Integration of Multi-Satellite Data and Deep Learning Models

Seo, Jae Young; Lee, Sang-Il

doi:10.1109/access.2021.3130306

Cited by 13 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Coactive ANFIS contributed into this field lately (Boo et al, 2024). Another study compares the predictive capabilities of LSTM, deep learning (DL) models, and CNN-Long Short-Term Memory (CNN-LSTM) (Seo & Lee, 2021), in characterizing GWS changes based on seismic data (Lähivaara et al, 2019), revealing the potential of DL for extracting insights from diverse data sources. A novel approach utilizing a regression-based framework predicted GWS images from monthly imageries (Hussein et al, 2020).…”

Section: Relevant Literaturementioning

confidence: 99%

Machine Learning for Groundwater Storage Prediction: Leveraging Climatic Variables

Md.,

2024

Preprint

View full text Add to dashboard Cite

Once abundant and readily available, groundwater (GW) is now dwindling at an alarming rate. This vital resource is under growing pressure from both natural and human-induced factors. Groundwater Level (GWL) is closely related to Groundwater Storage (GWS) thus the decline in GWL creates a shortage in GWS. This research developed a robust predictive model for GWS in Rajshahi district, Bangladesh, for the period 2001–2022 using six climatic variables, namely, Mean Temperature, Cloud Coverage, Humidity (percent), Solar Radiation, Sunshine, and Wind Speed. Three Machine Learning (ML)-based regression models- Random Forest (RF), Support Vector Machine (SVM), and Gradient Boosting Machine (GBM) were applied for this purpose. Results showed that the accuracy level was quite high while RF regression was plugged into the observed dataset (R2 = 0.80). Moreover, among the six climatic variables, cloud coverage, humidity, and wind speed contributed 87.4% altogether to predict the GWS. These findings offer valuable insights not only for understanding the GWS dynamics in Rajshahi district but also for informing sustainable management strategies. By providing decision-makers with a clear understanding of the key climatic drivers and their impact, this research empowers them to implement effective interventions and conservation measures to ensure the long-term availability of this critical resource.

show abstract

Section: Relevant Literaturementioning

confidence: 99%

Machine Learning for Groundwater Storage Prediction: Leveraging Climatic Variables

Md.,

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Other researchers have incorporated remote sensing data to address the temporal data scarcity. Seo and Lee [19] used multiple types of satellite data together with a long short term memory (LSTM) convolutional neural network for groundwater data imputation.…”

Section: Previous Workmentioning

confidence: 99%

Methods for Characterizing Groundwater Resources with Sparse In Situ Data

et al. 2022

View full text Add to dashboard Cite

Accurate characterization of groundwater resources is required for sustainable management. Due to the cost of installing monitoring wells and challenges in collecting and managing in situ data, groundwater data are sparse—especially in developing countries. In this study, we demonstrate an analysis of long-term groundwater storage changes using temporally sparse but spatially dense well data, where each well had as few as one historical groundwater measurement. We developed methods to synthetically estimate groundwater table elevation (WTE) times series by clustering wells using two different methods; a uniform grid and k-means-constrained clustering to create pseudo-wells. These pseudo-wells had a more complete groundwater level time history, which we then temporally and spatially interpolated to analyze groundwater storage changes in an aquifer. We demonstrated these methods on the Beryl-Enterprise aquifer in Utah, USA, where other researchers quantified the groundwater storage depletion rate, and the wells had a large number of historical measurements. We randomly used one measurement per well and showed that our methods yielded storage depletion rates similar to published values. We applied the method to a region in southern Niger where wells had only one measurement per well, and showed that our estimated groundwater storage change trend reasonably matched that which was calculated using GRACE satellite data.

show abstract

“…With the advent of the era of artificial intelligence, machine learning methods, which include long short-term memory networks and random forest (RF), have been gradually introduced into a wide range of fields, such as planetscope nanosatellites image classification ( 13 ), automated weed detection system ( 14 , 15 ), modeling of groundwater storage change ( 16 – 19 ), supervised image classification ( 20 ), and analysis of environmental factors ( 21 ), and have achieved good results. Therefore, machine learning methods have important applications in medical management, such as disease prediction.…”

Section: Introductionmentioning

confidence: 99%

A risk prediction model for type 2 diabetes mellitus complicated with retinopathy based on machine learning and its application in health management

et al. 2023

View full text Add to dashboard Cite

ObjectiveThis study aimed to establish a risk prediction model for diabetic retinopathy (DR) in the Chinese type 2 diabetes mellitus (T2DM) population using few inspection indicators and to propose suggestions for chronic disease management.MethodsThis multi-centered retrospective cross-sectional study was conducted among 2,385 patients with T2DM. The predictors of the training set were, respectively, screened by extreme gradient boosting (XGBoost), a random forest recursive feature elimination (RF-RFE) algorithm, a backpropagation neural network (BPNN), and a least absolute shrinkage selection operator (LASSO) model. Model I, a prediction model, was established through multivariable logistic regression analysis based on the predictors repeated ≥3 times in the four screening methods. Logistic regression Model II built on the predictive factors in the previously released DR risk study was introduced into our current study to evaluate the model’s effectiveness. Nine evaluation indicators were used to compare the performance of the two prediction models, including the area under the receiver operating characteristic curve (AUROC), accuracy, precision, recall, F1 score, balanced accuracy, calibration curve, Hosmer-Lemeshow test, and Net Reclassification Index (NRI).ResultsWhen including predictors, such as glycosylated hemoglobin A1c, disease course, postprandial blood glucose, age, systolic blood pressure, and albumin/urine creatinine ratio, multivariable logistic regression Model I demonstrated a better prediction ability than Model II. Model I revealed the highest AUROC (0.703), accuracy (0.796), precision (0.571), recall (0.035), F1 score (0.066), Hosmer-Lemeshow test (0.887), NRI (0.004), and balanced accuracy (0.514).ConclusionWe have built an accurate DR risk prediction model with fewer indicators for patients with T2DM. It can be used to predict the individualized risk of DR in China effectively. In addition, the model can provide powerful auxiliary technical support for the clinical and health management of patients with diabetes comorbidities.

show abstract

Predicting Changes in Spatiotemporal Groundwater Storage Through the Integration of Multi-Satellite Data and Deep Learning Models

Cited by 13 publications

References 45 publications

Machine Learning for Groundwater Storage Prediction: Leveraging Climatic Variables

Machine Learning for Groundwater Storage Prediction: Leveraging Climatic Variables

Methods for Characterizing Groundwater Resources with Sparse In Situ Data

A risk prediction model for type 2 diabetes mellitus complicated with retinopathy based on machine learning and its application in health management

Contact Info

Product

Resources

About