{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T06:42:12Z","timestamp":1780555332288,"version":"3.54.1"},"reference-count":60,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Korea Government","award":["RS-2024-00405278"],"award-info":[{"award-number":["RS-2024-00405278"]}]},{"name":"Regional Innovation System & Education"},{"name":"Jeju RISE Center"},{"name":"Ministry of Education"},{"name":"Jeju Special Self-Governing Province, Republic of Korea","award":["2025-RISE-17-001"],"award-info":[{"award-number":["2025-RISE-17-001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Greenhouse agriculture plays a vital role in sustainable food production but also entails challenges such as high energy consumption and significant carbon emissions. To address these issues and evaluate the feasibility of adopting alternative energy sources such as green hydrogen, it is essential to precisely understand the spatial structure of agricultural facilities and accurately predict their energy demands. However, effectively processing real-world datasets\u2014characterized by complex aerial imagery and severe class imbalance\u2014remains a technical challenge. This study proposes a deep learning-based framework for accurately detecting and segmenting greenhouses using high-resolution aerial images. To improve object detection performance, a class-weighted loss function and a class-aware sampling strategy were integrated into the You Only Look Once 8 (YOLOv8)\u00a0model to mitigate the effects of class imbalance. The proposed model achieved an overall mean average precision (mAP)@0.5:0.95 of 0.566, with precision increasing to 0.881 and recall improving to 0.822, demonstrating balanced and robust performance across classes. Additionally, the model was combined with the Segment Anything Model (SAM) to enhance segmentation precision, and its performance was compared against Open-World Localization Vision Transformer (OWL-ViT) + SAM and YOLOv8-only segmentation approaches. Experimental results show that the YOLOv8 + SAM (Fusion) configuration achieved the highest Intersection over Union (IoU) of 0.7588 and Dice coefficient (Dice) of 0.8578, demonstrating superior boundary accuracy and mask consistency compared to other methods. The joint application of class weighting and sampling improved recall for minority classes such as greenhouses, while SAM-based segmentation enhanced boundary fidelity and shape preservation. Based on the segmented areas, greenhouse surface areas were calculated, and a conservative energy consumption benchmark was applied to estimate annual energy demand. This research presents a practical baseline for evaluating the potential of renewable energy integration in agriculture and is expected to contribute to future strategies for achieving carbon neutrality and green hydrogen utilization in the agricultural sector.<\/jats:p>","DOI":"10.7717\/peerj-cs.3665","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T08:37:13Z","timestamp":1772613433000},"page":"e3665","source":"Crossref","is-referenced-by-count":1,"title":["Improved greenhouse segmentation\n                    <i>via<\/i>\n                    YOLOv8 and segment anything model for energy and hydrogen demand forecasting"],"prefix":"10.7717","volume":"12","author":[{"given":"Jiyoung","family":"Ko","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4759-0138","authenticated-orcid":true,"given":"Yong-Woon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1107-9941","authenticated-orcid":true,"given":"Yung-Cheol","family":"Byun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2026,3,4]]},"reference":[{"issue":"1","key":"10.7717\/peerj-cs.3665\/ref-1","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1016\/j.rser.2016.12.098","article-title":"Zero-energy hydrogen economy (ZEH2E) for buildings and communities including personal mobility","volume":"71","author":"Alanne","year":"2017","journal-title":"Renewable and Sustainable Energy Reviews"},{"key":"10.7717\/peerj-cs.3665\/ref-2","doi-asserted-by":"publisher","first-page":"108500","DOI":"10.1016\/j.compag.2024.108757","article-title":"Object detection and tracking in precision farming","volume":"225","author":"Ariza-Sent\u00eds","year":"2024","journal-title":"Computers and Electronics in Agriculture"},{"issue":"1","key":"10.7717\/peerj-cs.3665\/ref-3","doi-asserted-by":"publisher","first-page":"110695","DOI":"10.1016\/j.compeleceng.2025.110695","article-title":"Revolutionizing plant disease diagnosis through vision-based intelligence and next-generation computing","volume":"128","author":"Batool","year":"2025","journal-title":"Computers and Electrical Engineering"},{"issue":"4","key":"10.7717\/peerj-cs.3665\/ref-4","doi-asserted-by":"publisher","first-page":"113031","DOI":"10.1016\/j.jobe.2025.113031","article-title":"Improved YOLOv8 framework for efficient solar panel defect detection","volume":"111","author":"Batool","year":"2025","journal-title":"Journal of Building Engineering"},{"issue":"4","key":"10.7717\/peerj-cs.3665\/ref-5","doi-asserted-by":"publisher","first-page":"e2495","DOI":"10.7717\/peerj-cs.2495","article-title":"An enhanced lightweight T-Net architecture based on convolutional neural network (CNN) for tomato plant leaf disease classification","volume":"10","author":"Batool","year":"2024","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.3665\/ref-6","article-title":"The geojson format. Technical report","author":"Butler","year":"2016"},{"key":"10.7717\/peerj-cs.3665\/ref-7","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1016\/j.apenergy.2015.08.009","article-title":"Technical feasibility of a hybrid on-site H2 and renewable energy system for a zero-energy building with a H2 vehicle","volume":"158","author":"Cao","year":"2015","journal-title":"Applied Energy"},{"issue":"4","key":"10.7717\/peerj-cs.3665\/ref-8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tgrs.2023.3338699","article-title":"Few-shot rotation-invariant aerial image semantic segmentation","volume":"62","author":"Cao","year":"2023","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"issue":"4","key":"10.7717\/peerj-cs.3665\/ref-9","doi-asserted-by":"publisher","first-page":"103991","DOI":"10.1016\/j.rineng.2025.103991","article-title":"Leveraging generative adversarial networks for data augmentation to improve fault detection in wind turbines with imbalanced data","volume":"25","author":"Chatterjee","year":"2025","journal-title":"Results in Engineering"},{"issue":"1","key":"10.7717\/peerj-cs.3665\/ref-10","doi-asserted-by":"publisher","first-page":"5044","DOI":"10.1016\/j.egyr.2024.09.073","article-title":"Recent advances and applications of machine learning in the variable renewable energy sector","volume":"12","author":"Chatterjee","year":"2024","journal-title":"Energy Reports"},{"issue":"1","key":"10.7717\/peerj-cs.3665\/ref-11","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.1016\/j.neucom.2015.09.105","article-title":"Energy demand forecasting of the greenhouses using nonlinear models based on model optimized prediction method","volume":"174","author":"Chen","year":"2016","journal-title":"Neurocomputing"},{"key":"10.7717\/peerj-cs.3665\/ref-12","article-title":"Accelerating the hydrogen economy-the time is now","author":"Clean Hydrogen Partnership","year":"2023"},{"issue":"7","key":"10.7717\/peerj-cs.3665\/ref-13","doi-asserted-by":"publisher","first-page":"4376","DOI":"10.1109\/tcsvt.2021.3135013","article-title":"A transformer-based feature segmentation and region alignment method for UAV-view geo-localization","volume":"32","author":"Dai","year":"2021","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"11","key":"10.7717\/peerj-cs.3665\/ref-14","doi-asserted-by":"publisher","first-page":"7778","DOI":"10.1109\/tpami.2021.3117983","article-title":"Object detection in aerial images: a large-scale benchmark and challenges","volume":"44","author":"Ding","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.7717\/peerj-cs.3665\/ref-15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"issue":"3","key":"10.7717\/peerj-cs.3665\/ref-16","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/tits.2020.2972974","article-title":"Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods, and challenges","volume":"22","author":"Feng","year":"2020","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.7717\/peerj-cs.3665\/ref-17","first-page":"1440","article-title":"Fast R-CNN","author":"Girshick","year":"2015"},{"key":"10.7717\/peerj-cs.3665\/ref-18","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"key":"10.7717\/peerj-cs.3665\/ref-19","article-title":"Heating strategy to take advantage of off-peak electrical power rates","author":"GreenBuildingAdvisor","year":"2018"},{"key":"10.7717\/peerj-cs.3665\/ref-20","article-title":"Analysing the future demand, supply and transport of hydrogen","author":"Guidehouse","year":"2021"},{"key":"10.7717\/peerj-cs.3665\/ref-21","first-page":"2786","article-title":"ReDet: a rotation-equivariant detector for aerial object detection","author":"Han","year":"2021"},{"issue":"1","key":"10.7717\/peerj-cs.3665\/ref-22","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/tpami.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.7717\/peerj-cs.3665\/ref-23","article-title":"Korean government invests in greenhouse-based hydrogen, not just solar power","author":"Hankyoreh","year":"2024"},{"issue":"16","key":"10.7717\/peerj-cs.3665\/ref-24","doi-asserted-by":"publisher","first-page":"2930","DOI":"10.3390\/rs16162930","article-title":"AerialFormer: multi-resolution transformer for aerial image segmentation","volume":"16","author":"Hanyu","year":"2024","journal-title":"Remote Sensing"},{"key":"10.7717\/peerj-cs.3665\/ref-25","first-page":"13802","article-title":"Video OWL-ViT: temporally-consistent open-world localization in video","author":"Heigold","year":"2023"},{"issue":"4","key":"10.7717\/peerj-cs.3665\/ref-26","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1007\/s10278-019-00227-x","article-title":"Deep learning techniques for medical image segmentation: achievements and challenges","volume":"32","author":"Hesamian","year":"2019","journal-title":"Journal of Digital Imaging"},{"key":"10.7717\/peerj-cs.3665\/ref-27","article-title":"Passive house certification criteria","author":"International Passive House Association","year":"2024"},{"key":"10.7717\/peerj-cs.3665\/ref-28","article-title":"District heating and cooling conversion factors: 0.728 and 0.937 applied","author":"KHARN","year":"2024"},{"issue":"4","key":"10.7717\/peerj-cs.3665\/ref-29","doi-asserted-by":"publisher","first-page":"27","DOI":"10.11108\/kagis.2023.26.4.027","article-title":"Greenhouse detection using yolo algorithm on planetscope satellite imagery","volume":"26","author":"Kim","year":"2023","journal-title":"Journal of the Korean Association of Geographic Information Studies"},{"issue":"4","key":"10.7717\/peerj-cs.3665\/ref-30","doi-asserted-by":"publisher","first-page":"884","DOI":"10.3390\/en11040884","article-title":"Analysis of energy saving potential in high-performance building technologies under Korean climatic conditions","volume":"11","author":"Kim","year":"2018","journal-title":"Energies"},{"key":"10.7717\/peerj-cs.3665\/ref-31","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.7717\/peerj-cs.3665\/ref-32","article-title":"South Korea\u2019s official primary energy conversion factors","author":"Korea Energy Agency","year":"2024"},{"key":"10.7717\/peerj-cs.3665\/ref-33","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"10.7717\/peerj-cs.3665\/ref-34","article-title":"Geojson example\u2014leaflet.js","author":"Leaflet","year":"2024"},{"key":"10.7717\/peerj-cs.3665\/ref-35","first-page":"1829","article-title":"Oriented reppoints for aerial object detection","author":"Li","year":"2022"},{"issue":"8","key":"10.7717\/peerj-cs.3665\/ref-36","doi-asserted-by":"publisher","first-page":"2238","DOI":"10.3390\/s20082238","article-title":"UAV-YOLO: small object detection on unmanned aerial vehicle perspective","volume":"20","author":"Liu","year":"2020","journal-title":"Sensors"},{"issue":"16","key":"10.7717\/peerj-cs.3665\/ref-37","doi-asserted-by":"publisher","first-page":"2561","DOI":"10.3390\/ani13162561","article-title":"Toward sustainability: an overview of the use of green hydrogen in the agriculture and livestock sector","volume":"13","author":"Maganza","year":"2023","journal-title":"Animals"},{"key":"10.7717\/peerj-cs.3665\/ref-38","first-page":"728","article-title":"Simple open-vocabulary object detection","author":"Minderer","year":"2022"},{"key":"10.7717\/peerj-cs.3665\/ref-39","article-title":"The era of energy transition in agriculture and rural areas is coming","author":"News","year":"2024"},{"key":"10.7717\/peerj-cs.3665\/ref-40","doi-asserted-by":"publisher","first-page":"100701","DOI":"10.1016\/j.coche.2021.100701","article-title":"A green hydrogen economy for a renewable energy society","volume":"33","author":"Oliveira","year":"2021","journal-title":"Current Opinion in Chemical Engineering"},{"key":"10.7717\/peerj-cs.3665\/ref-41","article-title":"Passive house requirements","author":"Passive House Institute","year":"2024"},{"issue":"1","key":"10.7717\/peerj-cs.3665\/ref-42","doi-asserted-by":"publisher","first-page":"2437162","DOI":"10.1080\/21642583.2024.2437162","article-title":"Advanced segmentation models for automated capsicum peduncle detection in night-time greenhouse environments","volume":"12","author":"Paul","year":"2024","journal-title":"Systems Science & Control Engineering"},{"issue":"1","key":"10.7717\/peerj-cs.3665\/ref-43","doi-asserted-by":"publisher","first-page":"100243","DOI":"10.1016\/j.fraope.2025.100243","article-title":"Advancing capsicum detection in night-time greenhouse environments using deep learning models: comparative analysis and improved zero-shot detection through fusion with a single-shot detector","volume":"10","author":"Paul","year":"2025","journal-title":"Franklin Open"},{"issue":"6","key":"10.7717\/peerj-cs.3665\/ref-44","doi-asserted-by":"publisher","first-page":"108832","DOI":"10.1016\/j.compag.2024.108832","article-title":"Smart solutions for capsicum harvesting: unleashing the power of yolo for detection, segmentation, growth stage classification, counting, and real-time mobile identification","volume":"219","author":"Paul","year":"2024","journal-title":"Computers and Electronics in Agriculture"},{"key":"10.7717\/peerj-cs.3665\/ref-45","first-page":"649","article-title":"Utilizing fine-tuned YOLOv8 deep learning model for greenhouse capsicum detection and growth stage determination","author":"Paul","year":"2023"},{"issue":"8","key":"10.7717\/peerj-cs.3665\/ref-46","doi-asserted-by":"publisher","first-page":"343","DOI":"10.22441\/sinergi.2023.3.006","article-title":"Image segmentation in aerial imagery: a review","volume":"27","author":"Purwanto","year":"2023","journal-title":"SINERGI"},{"key":"10.7717\/peerj-cs.3665\/ref-47","first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.7717\/peerj-cs.3665\/ref-48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.09972","article-title":"Real-time flying object detection with YOLOv8","author":"Reis","year":"2023"},{"issue":"6","key":"10.7717\/peerj-cs.3665\/ref-49","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/tpami.2016.2577031","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.7717\/peerj-cs.3665\/ref-50","article-title":"Carbon-free island JEJU by 2030-observatory of public sector innovation","author":"Seo","year":"2023"},{"issue":"1","key":"10.7717\/peerj-cs.3665\/ref-51","doi-asserted-by":"publisher","first-page":"65","DOI":"10.3390\/en11010065","article-title":"Energy consumption prediction of a greenhouse and optimization of daily average temperature","volume":"11","author":"Shen","year":"2018","journal-title":"Energies"},{"key":"10.7717\/peerj-cs.3665\/ref-52","article-title":"Making Jeju Island carbon-free","author":"The Borgen Project","year":"2024"},{"key":"10.7717\/peerj-cs.3665\/ref-53","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.7717\/peerj-cs.3665\/ref-54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tgrs.2022.3186634","article-title":"Building extraction with vision transformer","volume":"60","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.7717\/peerj-cs.3665\/ref-55","first-page":"6450","article-title":"Aerial image object detection with vision transformer detector (VITDET)","author":"Wang","year":"2023"},{"key":"10.7717\/peerj-cs.3665\/ref-56","article-title":"Balance classes during YOLO training using a weighted dataloader. Yasin\u2019s Keep","author":"Yasin","year":"2024"},{"issue":"8","key":"10.7717\/peerj-cs.3665\/ref-57","doi-asserted-by":"publisher","first-page":"1643","DOI":"10.3390\/agriculture13081643","article-title":"Improved YOLOv8-SEG network for instance segmentation of healthy and diseased tomato plants in the growth stage","volume":"13","author":"Yue","year":"2023","journal-title":"Agriculture"},{"issue":"11","key":"10.7717\/peerj-cs.3665\/ref-58","doi-asserted-by":"publisher","first-page":"103514","DOI":"10.1016\/j.dsp.2022.103514","article-title":"A survey of modern deep learning based object detection models","volume":"126","author":"Zaidi","year":"2022","journal-title":"Digital Signal Processing"},{"key":"10.7717\/peerj-cs.3665\/ref-59","doi-asserted-by":"publisher","first-page":"2297","DOI":"10.1109\/JSTARS.2024.3501216","article-title":"A systematic review of the use of deep learning in satellite imagery for agricultural tasks","volume":"18","author":"Zhang","year":"2025","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"issue":"3","key":"10.7717\/peerj-cs.3665\/ref-60","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/jproc.2023.3238524","article-title":"Object detection in 20 years: a survey","volume":"111","author":"Zou","year":"2023","journal-title":"Proceedings of the IEEE"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3665.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3665.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3665.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3665.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T08:37:24Z","timestamp":1772613444000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3665"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,4]]},"references-count":60,"alternative-id":["10.7717\/peerj-cs.3665"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3665","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,4]]},"article-number":"e3665"}}