<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.2d1 20170631//EN" "JATS-journalpublishing1.dtd">
<ArticleSet>
<Article>
<Journal>
<PublisherName>ijesm</PublisherName>
<JournalTitle>International Journal of Engineering, Science and</JournalTitle>
<PISSN>I</PISSN>
<EISSN>S</EISSN>
<Volume-Issue>volume 15,issue 5</Volume-Issue>
<PartNumber/>
<IssueTopic>Multidisciplinary</IssueTopic>
<IssueLanguage>English</IssueLanguage>
<Season>May 2026</Season>
<SpecialIssue>N</SpecialIssue>
<SupplementaryIssue>N</SupplementaryIssue>
<IssueOA>Y</IssueOA>
<PubDate>
<Year>2026</Year>
<Month>05</Month>
<Day>10</Day>
</PubDate>
<ArticleType>Engineering, Science and Mathematics</ArticleType>
<ArticleTitle>ORBITAL__ampersandsign#8209;PARAMETER__ampersandsign#8209;CONDITIONED LSTM FOR ON__ampersandsign#8209;BOARD THERMAL LOAD FORECASTING IN 3U CUBESAT CONSTELLATIONS</ArticleTitle>
<SubTitle/>
<ArticleLanguage>English</ArticleLanguage>
<ArticleOA>Y</ArticleOA>
<FirstPage>1</FirstPage>
<LastPage>14</LastPage>
<AuthorList>
<Author>
<FirstName>David Santosh</FirstName>
<LastName>Christopher</LastName>
<AuthorLanguage>English</AuthorLanguage>
<Affiliation/>
<CorrespondingAuthor>N</CorrespondingAuthor>
<ORCID/>
<FirstName>Temesgen Hailegiorgis</FirstName>
<LastName>Abebe</LastName>
<AuthorLanguage>English</AuthorLanguage>
<Affiliation/>
<CorrespondingAuthor>Y</CorrespondingAuthor>
<ORCID/>
</Author>
</AuthorList>
<DOI/>
<Abstract>Accurate prediction of nanosatellite thermal loads in Low Earth Orbit (LEO) is essential to guarantee subsystem reliability and extend mission lifetime, especially for resource__ampersandsign#8209;constrained CubeSat constellations. Classical thermal tools based on finite__ampersandsign#8209;element or finite__ampersandsign#8209;difference models are too computationally intensive for on__ampersandsign#8209;board use and cannot adapt quickly to changing orbital conditions such as eclipse fraction, solar beta angle, or internal power dissipation. This work proposes an orbital__ampersandsign#8209;parameter__ampersandsign#8209;conditioned Long Short__ampersandsign#8209;Term Memory (LSTM) network for predictive thermal load forecasting in 3U CubeSat formations operating in sun__ampersandsign#8209;synchronous LEO orbits over the Indian Ocean Region (IOR). A physics__ampersandsign#8209;derived synthetic dataset of 5,000 scenarios is generated using a validated six__ampersandsign#8209;face lumped__ampersandsign#8209;capacitance thermal model coupled with RK45 orbital propagation, spanning altitudes from 450__ampersandsignndash;700 km, solar beta angles from __ampersandsignminus;75__ampersandsigndeg; to +75__ampersandsigndeg;, and three surface coating configurations</Abstract>
<AbstractLanguage>English</AbstractLanguage>
<Keywords>LSTM neural network; CubeSat thermal management; LEO orbital mechanics; predictive thermal control; nanosatellite formation flying; machine learning; thermal load forecasting.</Keywords>
<URLs>
<Abstract>https://www.ijesm.co.in/ubijournal-v1copy/journals/abstract.php?article_id=16232&title=ORBITAL__ampersandsign#8209;PARAMETER__ampersandsign#8209;CONDITIONED LSTM FOR ON__ampersandsign#8209;BOARD THERMAL LOAD FORECASTING IN 3U CUBESAT CONSTELLATIONS</Abstract>
</URLs>
<References>
<ReferencesarticleTitle>References</ReferencesarticleTitle>
<ReferencesfirstPage>16</ReferencesfirstPage>
<ReferenceslastPage>19</ReferenceslastPage>
<References/>
</References>
</Journal>
</Article>
</ArticleSet>