[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121257-en":3,"doc-seo-121257-105":30,"detail-sidebar-cat-0-en-105":95},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121257,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Tackling water table depth modeling via machine learning - From proxy observations to verifiability","Spatial patterns of water table depth (WTD) underpin ecological resilience, hydrological connectivity, and human-relevant systems. Large-scale static WTD maps can be simulated using physically-based or machine learning models. This work builds three 500 m fine-resolution XGBoost simulations across the United States and Canada, integrating over 20 million real and proxy observations. Constrained by physical driver–WTD relations, models are evaluated pixel-by-pixel and within ten major North American ecoregions, showing improved predictive accuracy over two PB baselines while highlighting uncertainty in data-scarce mountainous regions.","arXiv :2405 .04579v3 [ cs .LG] 13 Mar 2025  \nmanuscript submitted to a journal (non-peer reviewed draft)  \nTackling water table depth modeling via machine learning: From  \nproxy observations to verifiability  \nJoseph Janssen 1 , Ardalan Tootchi 1 , and Ali A. Ameli 1  \n1 Department of Earth, Ocean, and Atmospheric Sciences, University of British Columbia, Vancouver, BC, Canada  \nAbstract  \nSpatial patterns of water table depth (WTD) play a crucial role in shaping ecological resilience, hydrological connectivity, and human-centric systems. Generally, a large-scale (e.g., continental or global) continuous map of static WTD can be simulated using either physically-based (PB) or machine learning-based (ML) models. We construct three fine-resolution (500 m) ML simulations of WTD, using the XGBoost algorithm and more than 20 million real and proxy observations of WTD, across the United States and Canada. The three ML models were constrained using known physical relations between WTD’s drivers and WTD and were trained by sequentially adding real and proxy observations of WTD. Through an extensive (pixel-by-pixel) evaluation across the study region and within ten major ecoregions of North America, we demonstrate that our models (corr=0.6-0.75) can more accurately predict unseen real and proxy observations of WTD compared to two available PB simulations of WTD (corr=0.21-0.40) . However, we still argue that currently-available large-scale simulations of static WTD could be uncertain within datascarce regions such as steep mountainous regions. We reason that biased observational data mainly collected from low-elevation floodplains and the over-flexibility of available models can negatively affect the verifiability of large-scale simulations of WTD. Ultimately, we thoroughly discuss future directions that may help hydrogeologists decide how to improve machine learning-based WTD estimations. In particular, we advocate for the use of proxy satellite data, the incorporation of physical laws, the implementation of better model verification standards, the development of novel globally-available emergent indices, and the collection of more reliable observations.  \nKeywords: Machine learning, physically-based models, Groundwater, Water Table Depth, North America, Ecoregions, Model uncertainty, Observation uncertainty  \n1 Introduction  \nGroundwater is the most abundant source of liquid freshwater on Earth, with an important influence on above-ground processes (Gleeson et al., 2016) . Groundwater affects water quantity and quality in streams (Miguez-Macho & Fan, 2012; G. A. Ali et al., 2011), lakes (Vaheddoost & Aksoy, 2018; S. Xu et al., 2021; Ameli & Craig, 2014), and wetlands (Ameli & Creed, 2019, 2017), and regulates the behaviour of ecological and human-centric systems (Siebert et al., 2010; Huggins et al., 2023) . In riverine ecosystems, groundwater provides critical water supplies to plants in arid riparian and non-riparian areas, without which trees and plants would quickly deteriorate in drought conditions (Kibler et al., 2021; G. Xu et al., 2022) . The central property of groundwater at a particular location and the particular aquifer is the water table depth (WTD), defined as the depth below which the ground becomes fully saturated with water. Static WTD, which is the main focus of this paper, is defined as the long-term average (non-transient)  \nwater table depth at a given location. This quantity can vary by several orders of magnitude from one location to another. Although transient WTD simulations are often needed to form robust conclusions about hydrological processes, large-scale (e.g., continental and global scales) fine-resolution spatial estimates of static WTD, can be used as a good first-order approximation in order to inform (1) the direction of groundwater movement (Freeze & Cherry, 1979), including whether or not the roots of trees ina given location have access to water (Tai et al., 2018; Cooper et al., 2003; Schook et a","cbCaikT8BKiDdfOy","https://ap.wps.com/l/cbCaikT8BKiDdfOy","pdf",27945376,1,39,"English","en",105,"# Introduction\n## Groundwater and water table depth\n## Motivation for static WTD modeling\n## Prior modeling approaches\n## Study contributions","[{\"question\":\"Why is water table depth (WTD) important in environmental and human systems?\",\"answer\":\"WTD influences groundwater-driven water quantity and quality in streams, lakes, and wetlands, and it regulates ecological and human-centric behaviors. It also affects plant access to water in arid riparian areas.\"},{\"question\":\"How do the proposed machine learning simulations generate static WTD maps?\",\"answer\":\"The study constructs three 500 m XGBoost simulations using more than 20 million real and proxy observations. Models are constrained by known physical relations and trained by sequentially adding real and proxy WTD observations.\"},{\"question\":\"What evidence supports the models' predictive and verification capability?\",\"answer\":\"An extensive pixel-by-pixel evaluation and ecoregion-level assessment demonstrates correlations of about 0.6–0.75 for unseen real and proxy observations. This performance is substantially higher than two available physically-based simulations (corr=0.21–0.40).\"},{\"question\":\"What are the main sources of uncertainty in large-scale WTD simulations?\",\"answer\":\"Uncertainty is argued to be higher in data-scarce steep mountainous regions. Biased observational data from low-elevation floodplains and model over-flexibility can reduce verifiability.\"}]","Tackling water table depth modeling via machine learning - From proxy observations to verifiability | PDF",1785734687,98,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":90,"head_meta":92,"extra_data":94,"updated_unix":28},"tackling-water-table-depth-modeling-via-machine-learning-from-proxy-observations-to-verifiability","",{"@graph":36,"@context":89},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/tackling-water-table-depth-modeling-via-machine-learning-from-proxy-observations-to-verifiability/121257/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"Why is water table depth (WTD) important in environmental and human systems?","Question",{"text":75,"@type":76},"WTD influences groundwater-driven water quantity and quality in streams, lakes, and wetlands, and it regulates ecological and human-centric behaviors. It also affects plant access to water in arid riparian areas.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do the proposed machine learning simulations generate static WTD maps?",{"text":80,"@type":76},"The study constructs three 500 m XGBoost simulations using more than 20 million real and proxy observations. Models are constrained by known physical relations and trained by sequentially adding real and proxy WTD observations.",{"name":82,"@type":73,"acceptedAnswer":83},"What evidence supports the models' predictive and verification capability?",{"text":84,"@type":76},"An extensive pixel-by-pixel evaluation and ecoregion-level assessment demonstrates correlations of about 0.6–0.75 for unseen real and proxy observations. This performance is substantially higher than two available physically-based simulations (corr=0.21–0.40).",{"name":86,"@type":73,"acceptedAnswer":87},"What are the main sources of uncertainty in large-scale WTD simulations?",{"text":88,"@type":76},"Uncertainty is argued to be higher in data-scarce steep mountainous regions. Biased observational data from low-elevation floodplains and model over-flexibility can reduce verifiability.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]