[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85409-en":3,"doc-seo-85409-105":29,"detail-sidebar-cat-0-en-105":90},{"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":4,"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":13,"seo_description":14,"update_tm":27,"read_time":28},85409,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1782109480056885918",8,"Research & Report","Parameter estimation for land-surface models using Neural Physics","A novel inverse-modelling approach estimates parameters of a simple land-surface model by assimilating data into a differentiable, physics-based forward model built with convolutional operations. Governing equations are implemented in the Neural Physics framework, enabling direct gradient-based optimisation of time-dependent parameters without deriving or maintaining adjoint formulations. Parameters are obtained by minimising mismatch between predictions and synthetic or observational data. Experiments show single-depth soil-temperature observations constrain parameters poorly, while two depths yield reliable estimates though latent and sensible heat flux effects remain indistinguishable.","arXiv:2505.02979v4 [[physics. ao-ph](physics. ao-ph)] 10 Jul 2026  \nParameter estimation for land-surface models using Neural Physics  \nRuiyue Huanga , Claire E. Heaneyb,c , Maarten van Reeuwijka,∗  \na Department of Civil and Environmental Engineering, Imperial College London, SW7 2AZ London, UK b Department of Earth Science and Engineering, Imperial College London, SW7 2AZ London, UK c Imperial-X, Imperial College London, W12 7SL London, UK  \nAbstract  \nWe propose a novel inverse-modelling approach that estimates the parameters of a simple land-surface model (LSM) by assimilating data into a differentiable, physics-based forward model formulated using convolutional operations. The governing equations are expressed within the Neural Physics framework, allowing direct gradient-based optimisation of time-dependent parameters without the need to derive and maintain adjoint formulations. The model parameters are estimated by minimising the mismatch between model predictions and synthetic or observational data. Although differentiability is enabled through machine-learning libraries, the forward model itself remains entirely physics-based and neither the forward model nor the parameter estimation procedure involve training.  \nTo evaluate the approach, we first generate synthetic observations of soil temperature by running the forward model with known parameter values and subsequently treat these parameters as unknown in an inverse problem. We show that observations of soil temperature at a single depth are insufficient to reliably constrain the model parameters. Using observations at two depths, however, does yield reliable parameter estimates, although the individual contributions of latent and sensible heat fluxes cannot be distinguished.  \nWe also apply the approach to urban flux tower data from Phoenix, United States, and show that the thermal conductivity, volumetric heat capacity and the combined sensible-latent heat transfer coefficient can be reliably estimated whilst using an observed value for the effective surface albedo. The resulting model accurately predicts the outgoing longwave radiation, conductive soil fluxes and the combined sensible-latent heat fluxes, demonstrating that the Neural Physics framework can be used to accurately determine the parameters of the particular LSM used here. This model is intentionally simple and does not include, for example, a subsurface moisture model. This simplicity facilitates an exploration of parameter identifiability, confounding and equifinality.  \nKeywords: land-surface model, differentiable solver, parameter estimation  \n1. Introduction  \nThe exchange of momentum and thermal energy between the land surface and the atmosphere is of great importance to atmospheric processes and thermal comfort (Oke, 2017) . At present, such processes are typically modelled with land-surface models (LSMs) using meteorological forcing data and various parameters associated with the site. Many LSMs have been developed over the years, each differing in how they handle the urban surface, and in their modelling of various morphological, vegetation, hydrological and anthropogenic processes. Modern LSMs are capable of closely replicating the heterogeneous surface structure of cities (Lee and Lee, 2020; Krayenhoff and Voogt, 2007), and capturing the effects of various urban processes, such as urban heat storage and vegetation dynamics, using various soil, hydrological or vegetation models (Lipson et al., 2017; Arsenault et al., 2018) .  \n∗ Corresponding author  \nEmail address: [m.vanreeuwijk@imperial.ac.uk](m.vanreeuwijk@imperial.ac.uk) (Maarten van Reeuwijk)  \nHowever, larger complexity of LSMs does not always translate to better predictions (Grimmond et al., 2010, 2011; Lipson et al., 2024) . The Urban-PLUMBER project (Lipson et al., 2024) evaluated the performance of 30 LSMsin estimating surface fluxes at a suburban site in Melbourne, Australia. The study found that models with highly complex urban sc","cbCaioAsH7eVgL2Z","https://ap.wps.com/l/cbCaioAsH7eVgL2Z","pdf",848122,1,18,"English","en",105,"# Introduction\n## Land-surface modelling challenges\n## Need for reliable parameter estimation","[{\"question\":\"How does the proposed method estimate land-surface model parameters?\",\"answer\":\"It assimilates data into a differentiable, physics-based forward model expressed in the Neural Physics framework, then minimises the mismatch between model predictions and data using gradient-based optimisation.\"},{\"question\":\"Why are adjoint formulations not required in this approach?\",\"answer\":\"The Neural Physics framework provides differentiability through machine-learning libraries, so time-dependent parameters can be optimised directly with gradients from the differentiable forward model rather than maintaining adjoint equations.\"},{\"question\":\"What observational setup is needed to reliably constrain parameters in the soil-temperature experiments?\",\"answer\":\"Single-depth observations at one depth are insufficient for reliable parameter constraints, whereas using observations at two depths enables reliable parameter estimation, even though latent and sensible heat flux contributions cannot be distinguished.\"}]",1784203193,45,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"parameter-estimation-for-land-surface-models-using-neural-physics","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/parameter-estimation-for-land-surface-models-using-neural-physics/85409/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"How does the proposed method estimate land-surface model parameters?","Question",{"text":74,"@type":75},"It assimilates data into a differentiable, physics-based forward model expressed in the Neural Physics framework, then minimises the mismatch between model predictions and data using gradient-based optimisation.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Why are adjoint formulations not required in this approach?",{"text":79,"@type":75},"The Neural Physics framework provides differentiability through machine-learning libraries, so time-dependent parameters can be optimised directly with gradients from the differentiable forward model rather than maintaining adjoint equations.",{"name":81,"@type":72,"acceptedAnswer":82},"What observational setup is needed to reliably constrain parameters in the soil-temperature experiments?",{"text":83,"@type":75},"Single-depth observations at one depth are insufficient for reliable parameter constraints, whereas using observations at two depths enables reliable parameter estimation, even though latent and sensible heat flux contributions cannot be distinguished.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]