[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86566-en":3,"doc-seo-86566-105":30,"detail-sidebar-cat-0-en-105":83},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86566,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","Climate-Invariant Conformal Prediction Intervals for Multi-Horizon Solar and Wind Forecasting","Reliable uncertainty quantification is essential for integrating solar and wind generation into modern power systems, where operators must manage risk rather than rely solely on point forecasts. Existing probabilistic methods may lack finite-sample validity or need per-site recalibration, limiting transfer across climates. This paper introduces a heteroscedastic, asymmetric, group-conditional split-conformal framework using a bootstrap-diverse XGBoost ensemble to produce locally adaptive prediction intervals with distribution-free coverage. Evaluated across four distinct sites and horizons (1–12 hours) for both targets, it achieves near-nominal coverage and reduces Interval Score by up to 35% versus competitive baselines.","Climate-Invariant Conformal Prediction Intervals for Multi-Horizon Solar and Wind Forecasting  \nShreedhar Gangwar , Abhinav Bains, , and Banalaxmi Brahma,   \narXiv :2607 . 11470v1 [ stat .AP] 13 Jul 2026  \nAbstract—Reliable uncertainty quantification is essential for integrating solar and wind generation into modern power systems, where operators must weigh risk rather than act on point forecasts alone. Existing probabilistic methods, however, often either lack finite-sample validity or require per-site recalibration, so a single model rarely transfers across the diverse climates of a dispersed generation fleet. This paper proposes a heteroscedastic, asymmetric, group-conditional split-conformal framework built on a bootstrap-diverse XGBoost ensemble, producing prediction intervals that adapt in width to local difficulty while retaining distribution-free coverage guarantees. A single fixed specification, with no per-site or per-horizon tuning, is evaluated across four climatologically distinct sites spanning both hemispheres, at horizons of 1 to 12 hours, for both solar irradiance and wind speed. The framework holds near-nominal coverage on both targets and reduces the Interval Score by up to 35% relative to competitive baselines, with the calibration and sharpness of its intervals shown to be properties of the method rather than of site-specific tuning.  \nIndex Terms—Conformal prediction, uncertainty quantification, solar irradiance forecasting, wind speed forecasting, ensemble learning, prediction intervals, multi-horizon forecasting, renewable energy  \nI. INTRODUCTION  \nSolar and wind generation have become a part of modern power systems, making forecasting and operational planning much more difficult. Renewable resources are stochastic, highly weather-dependent, and therefore highly variable overtime scales. Predicting solar irradiance and wind speed is thus at the core of grid stability, energy trading, and resource allocation. However, accuracy alone is not sufficient; reliable uncertainty quantification is required to enable operators to manage the uncertainty and risk associated with their operations, rather than respond to it.  \nIn this context, the accuracy of point-forecasts has been significantly enhanced by machine learning, and deep models in particular are now able to predict wind power and ramp events well. However, most of these models only produce one deterministic result and do not offer a calibrated estimate of confidence, restricting their applicability in contexts where risk needs to be explicitly considered [1] . Conformal prediction (CP) directly tackles this problem by building prediction intervals with finite-sample coverage guarantees based on a mild exchangeability assumption [2] . Inductive CP makes the approach practical by calibrating on a held-out set instead of retraining, and conformalized quantile regression adapts  \nAll authors are with the Department of Computer Science and Engineering, Dr. B.R. Ambedkar National Institute of Technology Jalandhar, India (e-mail: [shreedhargangwar@gmail.com](shreedhargangwar@gmail.com); [abhinavbains@gmail.com](abhinavbains@gmail.com);  \n[brahmab@nitj.ac.in](brahmab@nitj.ac.in)).  \ninterval width to local difficulty under heteroscedasticity [3] . Ensemble extensions are developed by adding conformal calibration to bootstrap aggregation, to boost the robustness for nonstationary series [4] . A separate concern is that standard CP guarantees only marginal coverage, which can hide systematic over- and under-coverage across regions of the input space; normalized and Mondrian schemes recover approximate conditional validity by conditioning on a data-dependent partition [5] .  \nThe use of CP in time series introduces another challenge, as temporal dependence and distribution shift are not exchangeable properties. There are a number of frameworks that address this. The Ensemble Batch Prediction Intervals method is an extension of CP to dependent data that does not ","cbCainOB9YKADpMF","https://ap.wps.com/l/cbCainOB9YKADpMF","pdf",404682,3,1,10,"English","en",105,"# Abstract\n# Introduction\n## Problem setting and motivation\n## Background on conformal prediction\n## Related work on time series conformal methods\n## Research gap and contributions","[{\"question\":\"What targets and forecast horizons are evaluated in the paper?\",\"answer\":\"The framework is tested for both solar irradiance and wind speed forecasting at horizons from 1 to 12 hours. Evaluation uses a probabilistic protocol including Interval Score as a lead-time metric.\"}]",1784212671,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":28},"climate-invariant-conformal-prediction-intervals-for-multi-horizon-solar-and-wind-forecasting","",{"@graph":36,"@context":77},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"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":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/climate-invariant-conformal-prediction-intervals-for-multi-horizon-solar-and-wind-forecasting/86566/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"What targets and forecast horizons are evaluated in the paper?","Question",{"text":75,"@type":76},"The framework is tested for both solar irradiance and wind speed forecasting at horizons from 1 to 12 hours. Evaluation uses a probabilistic protocol including Interval Score as a lead-time metric.","Answer","https://schema.org",{"og:url":51,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,126],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":22,"slug":125},"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":98,"slug":129},19,"General","general"]