[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86190-en":3,"doc-seo-86190-105":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},86190,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Long-Memory Reservoir Computing for Data-Scarce Dengue Forecasting","Accurate dengue forecasting is vital for public health preparedness, yet incidence time series are often short, noisy, non-stationary, nonlinear, and shaped by long-range temporal dependence. Fractional differencing via ARFIMA mitigates non-stationarity but remains linear, while deep models need large samples and do not explicitly encode long memory. This study proposes long-memory reservoir computing using dedicated long- and short-memory ESN reservoirs with a ridge-regression readout. It introduces Fractional ESN and Wavelet ESN, provides closed-loop guarantees, and improves dengue predictions with calibrated uncertainty using conformal prediction.","arXiv :2607 . 11272v1 [ stat .ML] 13 Jul 2026  \nLong-Memory Reservoir Computing for Data-Scarce Dengue Forecasting  \nRahul Goswami [rahul.goswami@iitg. ac.in](rahul.goswami@iitg. ac.in)  \nDepartment of Mathematics, Indian Institute of Technology Guwahati, India SAFIR, Sorbonne University Abu Dhabi, United Arab Emirates  \nShinjini Paul [s.paul@math.leidenuniv.nl](s.paul@math.leidenuniv.nl)  \nLeiden University, Leiden, South Holland, Netherlands  \n[Palash Ghosh](Palash Ghosh palash.ghosh@iitg. ac.in)[ palash.ghosh@iitg. ac.in](Palash Ghosh palash.ghosh@iitg. ac.in)  \nDepartment of Mathematics, Indian Institute of Technology Guwahati, India  \nTanujit Chakraborty [tanujit. chakraborty@sorbonne. ae](tanujit. chakraborty@sorbonne. ae)  \nSAFIR, Sorbonne University Abu Dhabi, United Arab Emirates  \nSorbonne Center for Artificial Intelligence, Sorbonne University, Paris, France  \nAbstract  \nAccurate dengue forecasting is crucial for public health planning, but remains challenging because incidence series are often short, noisy, non-stationary, nonlinear, and often affected by long-range temporal dependence. Fractional differencing in Autoregressive Fractionally Integrated Moving Average (ARFIMA) helps balance non-stationarity and persistence, but its linear structure limits its ability to capture nonlinear dynamics. Deep neural networks can model nonlinear patterns, but usually require large training samples and do not explicitly encode statistical long memory. Echo State Networks (ESNs), a widely used reservoir computing framework, are attractive in this setting because they retain nonlinear recurrent dynamics while training only a simple readout, making them suitable for data-scarce scenarios. However, standard ESNs lack long-term memory from a time-series perspective.  \nThis study proposes a long-memory reservoir computing framework that integrates dedicated long-memory and short-memory ESN reservoirs with a ridge-regression readout. We introduce two variants: Fractional ESN (fESN), which incorporates fractional-differencing dynamics into the reservoir to encode long-range dependence directly, and Wavelet ESN (wESN), which extracts stable low-frequency components through wavelet smoothing before modeling them with a memory-aware reservoir. We establish theoretical guarantees for closed-loop reservoir dynamics, showing that standard ESNs induce short-memory processes under mild conditions, whereas the proposed long-memory reservoirs generate polynomially decaying dependence consistent with statistical long memory. Across multiple dengue datasets and forecasting horizons, fESN and wESN outperform statistical and deep learning baselines. Combining conformal prediction with fESN and wESN provides distributionfree calibrated uncertainty intervals for operational public health decision-making. The‘memory-esn’ Python package offers an implementation of our proposed approaches.  \n1 Introduction  \nDengue remains a major public health concern in many tropical and subtropical regions, where timely forecasting can support preparedness, resource allocation, vector-control planning, and early warning interventions (Halstead, 2007 ; Wearing & Rohani, 2006 ; Bhatt et al. , 2013) . Most infections cause a sudden onset of high fever, severe headache, muscle and joint pain, and skin rash. However, the illness can sometimes progress to dengue hemorrhagic fever (a severe form involving plasma leakage and bleeding) or dengue shock  \nsyndrome (a critical drop in blood pressure that can lead to organ failure and death if untreated) (Iqbal et al. , 2025) . The disease is prevalent in more than 100 countries, particularly in tropical and subtropical regions, placing roughly half of the world’s population at risk, with Asia alone accounting for about 70% of the global dengue burden (World Health Organization (WHO), 2025 ; Malaria Consortium, 2024) . Transmission occurs mainly through the bites of infected female Aedes aegypti mosquitoes, as well as Aedes albo","cbCaipPWaxZG5BVK","https://ap.wps.com/l/cbCaipPWaxZG5BVK","pdf",3533594,1,45,"English","en",105,"# Introduction\n## Motivation and challenges in dengue forecasting\n## Proposed long-memory reservoir computing framework\n## Methods and model variants (fESN, wESN)\n## Theoretical analysis of closed-loop reservoir dynamics\n## Experimental results on dengue datasets\n## Uncertainty quantification for operational decision-making","[{\"question\":\"Why is dengue forecasting difficult with existing approaches?\",\"answer\":\"Dengue incidence series are typically short, noisy, non-stationary and nonlinear, and they often exhibit long-range temporal dependence, which classical linear models and standard deep models handle only partially.\"},{\"question\":\"What long-memory reservoir computing framework does the study propose?\",\"answer\":\"It integrates dedicated long-memory and short-memory Echo State Network reservoirs and trains a ridge-regression readout, aiming to capture long-range dependence while retaining nonlinear recurrent dynamics.\"},{\"question\":\"How do fESN and wESN differ in handling long-range dependence?\",\"answer\":\"Fractional ESN (fESN) embeds fractional-differencing dynamics into the reservoir to encode long-range dependence directly, while Wavelet ESN (wESN) uses wavelet smoothing to extract stable low-frequency components before modeling with a memory-aware reservoir.\"}]",1784209260,113,{"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},"long-memory-reservoir-computing-for-data-scarce-dengue-forecasting","",{"@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/long-memory-reservoir-computing-for-data-scarce-dengue-forecasting/86190/",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},"Why is dengue forecasting difficult with existing approaches?","Question",{"text":74,"@type":75},"Dengue incidence series are typically short, noisy, non-stationary and nonlinear, and they often exhibit long-range temporal dependence, which classical linear models and standard deep models handle only partially.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What long-memory reservoir computing framework does the study propose?",{"text":79,"@type":75},"It integrates dedicated long-memory and short-memory Echo State Network reservoirs and trains a ridge-regression readout, aiming to capture long-range dependence while retaining nonlinear recurrent dynamics.",{"name":81,"@type":72,"acceptedAnswer":82},"How do fESN and wESN differ in handling long-range dependence?",{"text":83,"@type":75},"Fractional ESN (fESN) embeds fractional-differencing dynamics into the reservoir to encode long-range dependence directly, while Wavelet ESN (wESN) uses wavelet smoothing to extract stable low-frequency components before modeling with a memory-aware reservoir.","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"]