{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:10:48Z","timestamp":1780355448188,"version":"3.54.1"},"reference-count":26,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T00:00:00Z","timestamp":1766102400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Rapid urban expansion has heightened the demand for accurate, scalable, and real-time methods to assess tree health and the provision of ecosystem services. Urban trees are the major contributors to air-quality improvement and climate change mitigation; however, their monitoring is mostly constrained to inherently subjective and inefficient manual inspections. In order to break this barrier, we put forward a lightweight multimodal deep-learning framework that fuses RGB imagery with environmental and biometric sensor data for a combined evaluation of tree-health condition as well as the estimation of the daily oxygen production and CO2 absorption. The proposed architecture features an EfficientNet-B0 vision encoder upgraded with Mobile Inverted Bottleneck Convolutions (MBConv) and a squeeze-and-excitation attention mechanism, along with a small multilayer perceptron for sensor processing. A common multimodal representation facilitates a three-task learning set-up, thus allowing simultaneous classification and regression within a single model. Our experiments with a carefully curated dataset of segmented tree images accompanied by synchronized sensor measurements show that our method attains a health-classification accuracy of 92.03% while also lowering the regression error for O2 (MAE = 1.28) and CO2 (MAE = 1.70) in comparison with unimodal and multimodal baselines. The proposed architecture, with its 5.4 million parameters and an inference latency of 38 ms, can be readily deployed on edge devices and real-time monitoring platforms.<\/jats:p>","DOI":"10.3390\/s26010007","type":"journal-article","created":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T11:03:46Z","timestamp":1766142226000},"page":"7","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Lightweight Multimodal Fusion for Urban Tree Health and Ecosystem Services"],"prefix":"10.3390","volume":"26","author":[{"given":"Abror","family":"Buriboev","sequence":"first","affiliation":[{"name":"Department of AI-Software, Gachon University, Sujeong-Gu, Seongnam-si 13120, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Djamshid","family":"Sultanov","sequence":"additional","affiliation":[{"name":"Department of Infocommunication Engineering, Tashkent University of Information Technologies Named After Muhammad Al-Khwarizmi, Tashkent 100200, Uzbekistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4872-4265","authenticated-orcid":false,"given":"Ilhom","family":"Rahmatullaev","sequence":"additional","affiliation":[{"name":"Digital Technologies and Artificial Intelligence Development Research Institute, Tashkent 100125, Uzbekistan"},{"name":"Department of Exact Sciences, Kimyo International University in Tashkent, Tashkent 100121, Uzbekistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7146-2106","authenticated-orcid":false,"given":"Ozod","family":"Yusupov","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Samarkand State University, Samarkand 140104, Uzbekistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8324-1816","authenticated-orcid":false,"given":"Erali","family":"Eshonqulov","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Samarkand State University Named After Sharof Rashidov, Samarkand 140104, Uzbekistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dilshod","family":"Bekmuradov","sequence":"additional","affiliation":[{"name":"Department of Digital Technologies and AI, Tashkent Institute of Irrigation and Agricultural Mechanization Engineers, National Research University, Tashkent 100000, Uzbekistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nodir","family":"Egamberdiev","sequence":"additional","affiliation":[{"name":"Department of Convergence of Digital Technologies, Tashkent University of Information Technologies Named After Muhammad Al-Khwarizmi, Tashkent 100200, Uzbekistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6507-3081","authenticated-orcid":false,"given":"Andrew Jaeyong","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of AI-Software, Gachon University, Sujeong-Gu, Seongnam-si 13120, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Anwander, J., Brandmeier, M., Paczkowski, S., Neubert, T., and Paczkowska, M. (2024). Evaluating Different Deep Learning Approaches for Tree Health Classification Using High-Resolution Multispectral UAV Data in the Black Forest, Harz Region, and G\u00f6ttinger Forest. Remote Sens., 16.","DOI":"10.3390\/rs16030561"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"25732","DOI":"10.1038\/s41598-025-04479-2","article-title":"A fine-tuned EfficientNet-B0 convolutional neural network for accurate and efficient classification of apple leaf diseases","volume":"15","author":"Ali","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Hidalgo, M., Yanine, F., Galleguillos, R., Lagos, M., Sahoo, S.K., and Paredes, R. (2025). Limitations of Transfer Learning for Chilean Cherry Tree Health Monitoring: When Lab Results Do Not Translate to the Orchard. Processes, 13.","DOI":"10.3390\/pr13082559"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Khan, R.W.A., Shaheen, H., Islam Dar, M.E.U., Habib, T., Manzoor, M., Gillani, S.W., Al-Andal, A., Ayoola, J.O., and Waheed, M. (2025). A data-driven approach to forest health assessment through multivariate analysis and machine learning techniques. BMC Plant Biol., 25.","DOI":"10.1186\/s12870-025-06937-5"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"127680","DOI":"10.1016\/j.ufug.2022.127680","article-title":"The impact of vegetation and media on evapotranspiration in bioretention systems","volume":"74","author":"Nasrollahpour","year":"2022","journal-title":"Urban For. Urban Green."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Mouret, F., Morin, D., Planells, M., and Vincent-Barbaroux, C. (2025). Tree Species Classification at the Pixel Level Using Deep Learning and Multispectral Time Series in an Imbalanced Context. Remote Sens., 17.","DOI":"10.3390\/rs17071190"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Tagmatova, Z., Umirzakova, S., Kutlimuratov, A., Abdusalomov, A., and Im Cho, Y. (2025). A Hyper-Attentive Multimodal Transformer for Real-Time and Robust Facial Expression Recognition. Appl. Sci., 15.","DOI":"10.3390\/app15137100"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Amin, A., Kamilaris, A., and Karatsiolis, S. (2024). A weakly supervised multimodal deep learning approach for large-scale tree classification: A case study in Cyprus. Remote Sens., 16.","DOI":"10.3390\/rs16234611"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Abdusalomov, A., Umirzakova, S., Kutlimuratov, A., Mirzaev, D., Dauletov, A., Botirov, T., Zakirova, M., Mukhiddinov, M., and Cho, Y.I. (2025). Lightweight UAV-Based System for Early Fire-Risk Identification in Wild Forests. Fire, 8.","DOI":"10.3390\/fire8080288"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"108719","DOI":"10.1016\/j.compag.2024.108719","article-title":"Multi-task learning model for agricultural pest detection from crop-plant imagery: A Bayesian approach","volume":"218","author":"Amrani","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Rahman, A.U., Heinaro, E., Ahishali, M., and Junttila, S. (2025). Dual-Task Learning for Dead Tree Detection and Segmentation with Hybrid Self-Attention U-Nets in Aerial Imagery. arXiv.","DOI":"10.2139\/ssrn.5270129"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"17851","DOI":"10.1038\/s41598-024-68541-1","article-title":"A comprehensive multi-task deep learning approach for predicting metabolic syndrome with genetic, nutritional, and clinical data","volume":"14","author":"Lee","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_13","unstructured":"Lin, H., Nazari, M., and Zheng, D. (2024). PCTreeS: 3D Point Cloud Tree Species Classification Using Airborne LiDAR Images. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"21525","DOI":"10.1038\/s41598-024-72237-x","article-title":"Bayesian optimized multimodal deep hybrid learning approach for tomato leaf disease classification","volume":"14","author":"Khan","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Xiang, J.Z., Wang, Q.Y., Fang, Z.B., Esquivel, J.A., and Su, Z.X. (2025). A multi-modal deep learning approach for stress detection using physiological signals: Integrating time and frequency domain features. Front. Physiol., 16.","DOI":"10.3389\/fphys.2025.1584299"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"8536","DOI":"10.1109\/JSTARS.2025.3549977","article-title":"Pine Wilt Disease Monitoring Using Multimodal Remote Sensing Data and Feature Classification","volume":"18","author":"Ye","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Savinelli, B., Tagliabue, G., Vignali, L., Garzonio, R., Gentili, R., Panigada, C., and Rossini, M. (2024). Integrating Drone-Based LiDAR and Multispectral Data for Tree Monitoring. Drones, 8.","DOI":"10.3390\/drones8120744"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1007\/s40725-024-00223-7","article-title":"LiDAR data fusion to improve forest attribute estimates: A review","volume":"10","author":"Balestra","year":"2024","journal-title":"Curr. For. Rep."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Du, Z., Wu, S., Wen, Q., Zheng, X., Lin, S., and Wu, D. (2024). Pine wilt disease detection algorithm based on improved YOLOv5. Front. Plant Sci., 15.","DOI":"10.3389\/fpls.2024.1302361"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Yang, C., Lu, J., Fu, H., Guo, W., Shao, Z., Li, Y., Zhang, M., Li, X., and Ma, Y. (2025). Detection of Pine Wilt Disease-Infected Dead Trees in Complex Mountainous Areas Using Enhanced YOLOv5 and UAV Remote Sensing. Remote Sens., 17.","DOI":"10.3390\/rs17172953"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"111655","DOI":"10.1016\/j.engappai.2025.111655","article-title":"Enhancing pine wilt disease detection with synthetic data and external attention-based transformers","volume":"159","author":"Amin","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, L., Di, D., Wang, J., Chen, G., Jing, W., and Emam, M. (2022). SERNet: Squeeze and excitation residual network for semantic segmentation of high-resolution remote sensing images. Remote Sens., 14.","DOI":"10.3390\/rs14194770"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Bansal, P., Kumar, R., and Kumar, S. (2021). Disease detection in apple leaves using deep convolutional neural network. Agriculture, 11.","DOI":"10.3390\/agriculture11070617"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Buriboev, A.S., Abduvaitov, A., and Jeon, H.S. (2025). Integrating Color and Contour Analysis with Deep Learning for Robust Fire and Smoke Detection. Sensors, 25.","DOI":"10.3390\/s25072044"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5510220","DOI":"10.1109\/TGRS.2025.3553751","article-title":"A Multitask Deep Learning Model for Classification and Regression of Hyperspectral Images: Application to a large scale dataset","volume":"63","author":"Chhapariya","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Mamadmurodov, A., Umirzakova, S., Rakhimov, M., Kutlimuratov, A., Temirov, Z., Nasimov, R., Meliboev, A., Abdusalomov, A., and Im Cho, Y. (2025). A Hybrid Deep Learning Model for Early Forest Fire Detection. Forests, 16.","DOI":"10.3390\/f16050863"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/7\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T11:08:18Z","timestamp":1766142498000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,19]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26010007"],"URL":"https:\/\/doi.org\/10.3390\/s26010007","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,19]]}}}