[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124927-en":3,"doc-seo-124927-105":30,"detail-sidebar-cat-0-en-105":91},{"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":27,"seo_description":14,"update_tm":28,"read_time":29},124927,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","Site-specific Deterministic Temperature and Humidity Forecasts with Explainable and Reliable Machine Learning","Site-specific weather forecasts are critical for improving power demand prediction, yet current numerical weather prediction models often lack fine spatial detail and remain limited to gridbox area averages. This study develops a site-optimized machine learning approach using gradient boosting decision trees via XGBoost, training regression trees on historical NWP outputs together with station observations to predict temperature and dew point at multiple Australian locations. Results show significant gains over bias-corrected gridded forecasts. Using SHAP-based interpretability, the study evaluates explanation and reliability strategies to increase trust in machine-learned predictions.","Site-specific Deterministic Temperature and Humidity Forecasts with Explainable and Reliable Machine Learning  \nMengMeng Han 1, Tennessee Leeuwenburg2*, Brad Murphy2  \n1 Bureau of Meteorology, 32 Turbot St, Brisbane City, QLD 4000, Australia  \n2 Bureau of Meteorology, 700 Collins St, Docklands, VIC 3008, Australia  \nPREPRINT, 4 APRIL2024  \nABSTRACT  \nSite-specific weather forecasts are essential to accurate prediction of power demand and are consequently of great interest to energy operators. However, weather forecasts from current numerical weather prediction (NWP) models lack the fine-scale detail to capture all important characteristics of localised real-world sites. Instead they provide weather information representing a rectangular gridbox (usually kilometres in size). Even after post-processing and bias correction, areaaveraged information is usually not optimal for specific sites. Prior work on site optimised forecasts has focused on linear methods, weighted consensus averaging, time-series methods, and others.  \nRecent developments in machine learning (ML) have prompted increasing interest in applying MLas a novel approach towards this problem. In this study, we investigate the feasibility of optimising forecasts at sites by adopting the popular machine learning model gradient boosting decision tree , supported by the Python version of the XGBoost package. Regression trees have been trained with historical NWP and site observations as training data, aimed at predicting temperature and dew point at multiple site locations across Australia. We developed a working ML framework, named 'MultiSiteBoost' and initial testing results show a significant improvement compared with gridded values from bias-corrected NWP models. The improvement from XGBoost is found to be comparable with non-ML methods reported in literature. With the insights provided by SHapley Additive exPlanations (SHAP), this study also tests various approaches to understand the ML predictions and increase the reliability of the forecasts generated by ML.  \nKEYWORDS: weather forecast; gradient boosting decision tree; machine learning; XGBoost;  \nNWP post-processing; SHAP  \n1 Introduction  \nDespite continual improvements in Numerical Weather Prediction (NWP) over several decades, with high skill in forecasts of some parameters out to a week or more ahead, shortcomings in weather forecasts remain. These include model biases, random errors, and representativeness errors, and tend to grow with forecast lead time. Systematic biases can be corrected through post-processing (Vannitsem, et al. 2021), though random errors will remain so there will always be a level of uncertainty in a forecast. Deterministic, or single-value forecasts, produce one estimate of a forecast value, so ensembles of multiple forecasts, designed to capture the spread in possible outcomes, are increasingly being used to produce probabilistic forecasts (e.g. Richardson, 2000) . These forecasts still typically represent a discrete area at least several kilometres in size, although this is decreasing as processing power grows. Model output at any current scale may not be representative of a specific site due to complex topography, land cover, urbanisation, or other local factors. A means of calibration between model forecasts and measured values at specific sites can improve this representation of  \nspecific locations. Methods for such calibration include those which alter forecast probability density functions to match that of the observed values (Bakker et al. 2019, Yang 2019, Alerskans and Kaas 2021) .  \nIn addition to conventional statistical methods, various machine learning (ML) and deep learning (DL) models have also been experimented with for the task of site-specific weather forecasting. Site-specific weather forecasts are optimised for a specific individual weather observing station. The term 'local' weather forecast may refer to a sitespecific forecast or to a small 'local' geographic ar","cbCaijfLmr57OQri","https://ap.wps.com/l/cbCaijfLmr57OQri","pdf",4676434,1,27,"English","en",105,"# Introduction\n## Motivation and limitations of gridded NWP forecasts\n## Calibration for site representation\n## Machine learning approaches for site-specific forecasting\n# MultiSiteBoost framework and experimental setup\n## Gradient boosting decision trees with XGBoost\n## Training with NWP and station observations\n# Explainability and reliability assessment\n## SHAP-based analysis of predictions","[{\"question\":\"Why are site-specific weather forecasts important for energy demand prediction?\",\"answer\":\"Site-specific forecasts improve the representation of local conditions that directly affect power demand. Gridbox NWP outputs often miss fine-scale site characteristics, reducing forecast usefulness.\"},{\"question\":\"How does the proposed method generate temperature and dew point forecasts at sites?\",\"answer\":\"It trains an XGBoost gradient boosting decision tree model (regression trees) using historical NWP data and site observations to predict temperature and dew point at multiple station locations.\"},{\"question\":\"What role does SHAP play in this study?\",\"answer\":\"SHAP provides explanation signals for the machine learning predictions, and the study evaluates different explanation approaches to improve the reliability and interpretability of the forecasts.\"}]","Site-specific Deterministic Temperature and Humidity Forecasts with Explainable and Reliable Machine Learning | PDF",1785895423,68,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"site-specific-deterministic-temperature-and-humidity-forecasts-with-explainable-and-reliable-machine-learning","",{"@graph":36,"@context":85},[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/site-specific-deterministic-temperature-and-humidity-forecasts-with-explainable-and-reliable-machine-learning/124927/",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","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are site-specific weather forecasts important for energy demand prediction?","Question",{"text":75,"@type":76},"Site-specific forecasts improve the representation of local conditions that directly affect power demand. Gridbox NWP outputs often miss fine-scale site characteristics, reducing forecast usefulness.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method generate temperature and dew point forecasts at sites?",{"text":80,"@type":76},"It trains an XGBoost gradient boosting decision tree model (regression trees) using historical NWP data and site observations to predict temperature and dew point at multiple station locations.",{"name":82,"@type":73,"acceptedAnswer":83},"What role does SHAP play in this study?",{"text":84,"@type":76},"SHAP provides explanation signals for the machine learning predictions, and the study evaluates different explanation approaches to improve the reliability and interpretability of the forecasts.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]