[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85850-en":3,"doc-seo-85850-105":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":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},85850,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Exploratory Analysis of Deep Learning Models for Forecasting Meteorological Parameters in the Agricultural Sector","Accurate meteorological forecasting underpins agricultural planning, irrigation management, and environmental decision support. This study compares recurrent and hybrid deep learning architectures for multivariate prediction of reference evapotranspiration (ET0), vapour pressure deficit (VPD), wind speed, and wind direction components (sine/cosine). Using 134,376 hourly observations from Ioannina, Greece (Jan 2011–Apr 2026) from ERA5 via OpenMeteo Historical Weather API, models are assessed on 24-hour and 168-hour horizons with normalized RMSE, R2, and a Weighted Quotient Score (WQS), highlighting hybrid CNN feature extraction benefits.","Exploratory Analysis of Deep Learning Models for Forecasting Meteorological  \nParameters in the Agricultural Sector  \nPiotr Sikora  \nFaculty of Technical Physics, Information Technology and Applied Mathematics Lodz Universtiy of Technlogy  \n[247784@edu.p.lodz.pl](247784@edu.p.lodz.pl)  \nSotirios Kontogiannis* MicroComputer Systems Laboratory  \n[https://kalipso.math.uoi.gr](https://kalipso.math.uoi.gr)  \nDept. of Mathematics University of Ioannina  \n[skontog@uoi.gr](skontog@uoi.gr)  \narXiv :2607 . 10208v 1 [ cs .LG] 11 Jul 2026  \nAbstract  \nAccurate meteorological forecasting is essential for agricultural planning, irrigation management, and environmental decision support. This study conducts a comparative evaluation of recurrent and hybrid deep learning architectures for multivariate forecasting of reference evapotranspiration (ET0 ), vapour pressure deficit (VPD), wind speed, and the sine and cosine components of wind direction. The analysis utilizes 134,376 hourly observations from Ioannina, Greece, spanning January 2011 to April 2026, sourced from ERA5 via the OpenMeteo Historical Weather API. Single and multi-layer GRU and LSTM networks are compared with hybrid 1D-CNN-GRU and 1D-CNN-LSTM models for two forecasting tasks: a 24-hour next-day forecast and a 168-hour week-ahead forecast. Performance is evaluated using normalized root mean squared error, the coefficient of determination, and a composite Weighted Quotient Score (WQS) . The most effective purely recurrent models are a 64-unit LSTMfor the 24-hour horizon, with a WQS of 0.816755, and a 1024-unit GRUfor the 168-hour horizon, with a WQS of 0.779465. The hybrid CNN-GRU models achieved the highest overall scores of 0.827535 and 0.782863 for the 24-hour and 168-hour horizons, but with additionally more number of units respectively to LSTM models, while the CNN-LSTM models yield nearly identical results with substantially fewer parameters. Compared to the corresponding recurrent baselines, the hybrid models improve WQS by 1.22–1.63% at 24 hours and by 0.44– 0. 45% at 168 hours, indicating that convolutional feature extraction is more beneficial for short-term forecasting.  \n1. Introduction  \nAccurate meteorological forecasting is critical for agricultural planning, irrigation scheduling, crop-water manage-  \n* Correspondence to: [skontog@uoi.gr](skontog@uoi.gr)  \nment, and the timely identification of atmospheric conditions that contribute to plant stress. Reference evapotranspiration (ET0 ) serves as a standardized indicator of atmospheric water demand and is a fundamental parameter for estimating crop-water requirements [1, 17] . Vapour pressure deficit (VPD) quantifies the difference between saturation and actual vapour pressure, and is closely linked to plant transpiration, water use, and crop response to atmospheric dryness [4, 21] . Wind speed and direction are also significant, as they affect the aerodynamic component of evapotranspiration and influence the transport and spatial distribution of heat and moisture. Joint forecasting of these variables can therefore facilitate more informed and timely agricultural decision-making.  \nDeep learning methods are increasingly utilized in meteorological and environmental forecasting due to their capacity to model nonlinear relationships and capture longrange temporal dependencies. At the global scale, models such as GraphCast have demonstrated the effectiveness of data-driven approaches for medium-range weather prediction [14] . At station and regional scales, recurrent neural networks have been employed to predict individual meteorological and agrohydrological variables. Specifically, LSTM and bidirectional LSTM models have been applied to daily and multi-step ET0 forecasting [17], while recent studies have compared LSTM, temporal convolutional networks, and N-BEATS for reference-evapotranspiration estimation and forecasting [18] . Machine-learning techniques have also been investigated for VPD prediction to support agric","cbCaiflBDRnj8qYa","https://ap.wps.com/l/cbCaiflBDRnj8qYa","pdf",1339578,2,1,13,"English","en",105,"# Abstract\n# Introduction\n# Methodology and Data\n# Experiments and Evaluation\n# Results and Discussion\n# Conclusion","[{\"question\":\"Which meteorological and derived variables are jointly forecast in this study?\",\"answer\":\"The study jointly forecasts reference evapotranspiration (ET0), vapour pressure deficit (VPD), wind speed, and wind direction represented by sine and cosine components.\"},{\"question\":\"What deep learning architectures are compared for the forecasting tasks?\",\"answer\":\"Single- and multi-layer GRU and LSTM models are compared against hybrid 1D-CNN-GRU and 1D-CNN-LSTM models.\"},{\"question\":\"How are model performances evaluated for the two forecasting horizons?\",\"answer\":\"Performance is measured using normalized RMSE, the coefficient of determination (R2), and a composite Weighted Quotient Score (WQS) for both 24-hour next-day and 168-hour week-ahead horizons.\"}]",1784206690,33,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"exploratory-analysis-of-deep-learning-models-for-forecasting-meteorological-parameters-in-the-agricultural-sector","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/exploratory-analysis-of-deep-learning-models-for-forecasting-meteorological-parameters-in-the-agricultural-sector/85850/",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","2026-07-22","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Which meteorological and derived variables are jointly forecast in this study?","Question",{"text":75,"@type":76},"The study jointly forecasts reference evapotranspiration (ET0), vapour pressure deficit (VPD), wind speed, and wind direction represented by sine and cosine components.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What deep learning architectures are compared for the forecasting tasks?",{"text":80,"@type":76},"Single- and multi-layer GRU and LSTM models are compared against hybrid 1D-CNN-GRU and 1D-CNN-LSTM models.",{"name":82,"@type":73,"acceptedAnswer":83},"How are model performances evaluated for the two forecasting horizons?",{"text":84,"@type":76},"Performance is measured using normalized RMSE, the coefficient of determination (R2), and a composite Weighted Quotient Score (WQS) for both 24-hour next-day and 168-hour week-ahead horizons.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"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"]