{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T17:02:55Z","timestamp":1772470975366,"version":"3.50.1"},"reference-count":63,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Accurate forecasting of nutrition supply\u2013demand dynamics is essential for reducing resource wastage and improving equitable allocation. However, this task remains challenging due to heterogeneous data sources, cold-start regions, and the risk of information leakage in spatiotemporal modeling. This study presents a leakage-aware multimodal machine learning framework for nutrition supply\u2013demand forecasting. The framework integrates temporal, spatial, and contextual information within a unified architecture. It combines self-supervised temporal representation learning, causal time-lag modeling, and few-shot adaptation to improve generalization under limited or previously unseen data conditions. Heterogeneous inputs include epidemiological, environmental, demographic, sentiment, and biologically derived indicators. These signals are encoded using a PatchTST-inspired temporal backbone coupled with a feature-token transformer employing cross-modal attention. Spatial dependencies are explicitly modeled using graph neural networks. Hierarchical decoding enables multi-horizon forecasting with calibrated uncertainty estimates. Model evaluation is conducted under strict spatiotemporal hold-out protocols with explicit leakage detection. All synthetic signals are excluded from testing. Across geographically and temporally disjoint datasets, the proposed framework consistently outperforms strong unimodal and multimodal baselines. It achieves macro-F1 scores above 99.5% and stable early-warning lead times of approximately 9 days under distribution shift. Ablation studies indicate that causal time-lag enforcement and few-shot adaptation contribute most strongly to performance robustness. Closed-loop simulation experiments suggest potential reductions in nutrient wastage of approximately 38%, response latency of 19%, and operational costs of 16% when deployed as a decision-support tool. External validation on fully unseen regions confirms the generalizability of the framework under realistic forecasting constraints.<\/jats:p>","DOI":"10.3390\/computers15030156","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T16:06:59Z","timestamp":1772467619000},"page":"156","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Leakage-Aware Multimodal Machine Learning Framework for Nutrition Supply\u2013Demand Forecasting Using Temporal and Spatial Data Fusion"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7983-2189","authenticated-orcid":false,"family":"Abdullah","sequence":"first","affiliation":[{"name":"Center for Computing Research, Instituto Polit\u00e9cnico Nacional, Mexico City 07738, Mexico"},{"name":"Department of Computer Sciences, Bahria University, Lahore 54600, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5397-6768","authenticated-orcid":false,"given":"Muhammad Ateeb","family":"Ather","sequence":"additional","affiliation":[{"name":"Department of Computer Sciences, Bahria University, Lahore 54600, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose Luis Oropeza","family":"Rodriguez","sequence":"additional","affiliation":[{"name":"Center for Computing Research, Instituto Polit\u00e9cnico Nacional, Mexico City 07738, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6935-2870","authenticated-orcid":false,"given":"Carlos Guzm\u00e1n","family":"S\u00e1nchez-Mejorada","sequence":"additional","affiliation":[{"name":"Center for Computing Research, Instituto Polit\u00e9cnico Nacional, Mexico City 07738, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8289-6979","authenticated-orcid":false,"given":"Miguel Jes\u00fas Torres","family":"Ruiz","sequence":"additional","affiliation":[{"name":"Center for Computing Research, Instituto Polit\u00e9cnico Nacional, Mexico City 07738, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4454-8791","authenticated-orcid":false,"given":"Rolando Quintero","family":"Tellez","sequence":"additional","affiliation":[{"name":"Center for Computing Research, Instituto Polit\u00e9cnico Nacional, Mexico City 07738, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Baldi, S.L., Bernotti, I., Dall\u2019Olio, L., Perrone, P.M., and Raviglione, M.C.B. (2025). Global Health: Principles and Perspectives. Handbook of Concepts in Health, Health Behavior and Environmental Health, Springer Nature.","DOI":"10.1007\/978-981-97-0821-5_110-1"},{"key":"ref_2","first-page":"1407","article-title":"Study to Evaluate Role of Digital Technology and Mobile Applications in Agoraphobic Patient Lifestyle","volume":"32","author":"Abdullah","year":"2025","journal-title":"J. Popul. Ther. Clin. Pharmacol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1657","DOI":"10.30574\/ijsra.2025.14.2.0564","article-title":"Strategies to Address Food Insecurity and Improve Global Nutrition Among At-Risk Populations","volume":"14","author":"Kunlere","year":"2025","journal-title":"Int. J. Sci. Res. Arch."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Touat, O. (2024). Global Supply Chain Disruptions: Lessons From the COVID-19 Pandemic Crisis. Business Resilience and Market Adaptability: Pandemic Effects and Strategies for Recovery, Springer Nature.","DOI":"10.1007\/978-981-97-2962-3_7"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1428","DOI":"10.30574\/ijsra.2025.14.2.0563","article-title":"Systemic Financial Risks in an Era of Geopolitical Tensions, Climate Change, and Technological Disruptions: Predictive Analytics, Stress Testing and Crisis Response Strategies","volume":"14","author":"Dugbartey","year":"2025","journal-title":"Int. J. Sci. Res. Arch."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ogwu, M.C., Izah, S.C., Ntuli, N.R., and Odubo, T.C. (2024). Food Security Complexities in the Global South. Food Safety and Quality in the Global South, Springer Nature.","DOI":"10.1007\/978-981-97-2428-4"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1146\/annurev-resource-100516-053552","article-title":"Transitioning Toward Nutrition-Sensitive Food Systems in Developing Countries","volume":"9","author":"Pingali","year":"2017","journal-title":"Annu. Rev. Resour. Econ."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"104S","DOI":"10.1177\/10806032251349436","article-title":"Methodologic Opportunities for Space Health Research: Integrating Biological Anthropology Methods in Human Research for Precision Space Health and Medical Data","volume":"36","author":"Sarma","year":"2025","journal-title":"Wilderness Environ. Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2910","DOI":"10.1021\/acsmaterialslett.5c00238","article-title":"Biocircuitry and Living Programmable Materials: The Next Frontier in Synthetic Living Systems","volume":"7","year":"2025","journal-title":"ACS Mater. Lett."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Xie, M., Wang, J., Wang, F., Wang, J., Yan, Y., Feng, K., and Chen, B. (2025). A Review of Genomic, Transcriptomic, and Proteomic Applications in Edible Fungi Biology: Current Status and Future Directions. J. Fungi, 11.","DOI":"10.3390\/jof11060422"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"636","DOI":"10.64252\/y86v7b35","article-title":"Therapeutic Role of Medicinal Plants in Combating Air Pollution-Induced Inflammation and Anxiety","volume":"11","author":"Rathore","year":"2025","journal-title":"Int. J. Environ. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Itrat, N., Israr, B., Arif, S., Narjis, M., Asghar, S., and Ali, A. (2025). Nutrient Absorption Dynamics and Food Contamination. Physiological Perspectives on Food Safety: Exploring the Intersection of Health and Nutrition, Springer Nature.","DOI":"10.1007\/978-3-031-94582-3_3"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Fatima, N., Yaqoob, S., Rana, L., Imtiaz, A., Iqbal, M.J., Bashir, Z., and Ma, Y. (2025). Micro-nutrient Sufficiency in Mothers and Babies: Management of Deficiencies While Avoiding Overload During Pregnancy. Front. Nutr., 12.","DOI":"10.3389\/fnut.2025.1476672"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Maitra, S., Behera, H.C., Bose, A., Chatterjee, D., and Bandyopadhyay, A.R. (2025). From Cultural Dispositions to Biological Dimensions: A Narrative Review on the Synergy Between Oral Health and Vitamin D Through the Lens of Indian Habitus. Front. Oral Health, 6.","DOI":"10.3389\/froh.2025.1569940"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1007\/s10462-025-11309-4","article-title":"Advances in Artificial Intelligence for Olfaction and Gustation: A Comprehensive Review","volume":"58","author":"Hao","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_16","unstructured":"Deng, O., and Jin, Q. (2025). Position: Public Health Systems Should Embrace a Multi-Layered Epidemic Early-Warning with LLM Agents and Local Knowledge Enhancement. Preprint."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ateeb Ather, M., Kolesnikova, O., and Sidorov, G. (2025). Detection of Biased Phrases in the Wiki Neutrality Corpus for Fairer Digital Content Management Using Artificial Intelligence. Big Data Cogn. Comput., 9.","DOI":"10.3390\/bdcc9070190"},{"key":"ref_18","first-page":"21","article-title":"Nutritional Content Detection Using Vision Transformers An Intelligent Approach","volume":"11","author":"Banerjee","year":"2024","journal-title":"Int. J. Innov. Res. Eng. Manag."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ding, H., Hou, H., Wang, L., Cui, X., Yu, W., and Wilson, D.I. (2025). Application of Convolutional Neural Networks and Recurrent Neural Networks in Food Safety. Foods, 14.","DOI":"10.3390\/foods14020247"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Long, Y., Kroeger, S., Zaeh, M.F., and Brintrup, A. (2025). Leveraging Synthetic Data to Tackle Machine Learning Challenges in Supply Chains: Challenges, Methods, Applications, and Research Opportunities. Int. J. Prod. Res., 122.","DOI":"10.1080\/00207543.2024.2447927"},{"key":"ref_21","unstructured":"Lin, C., Ma, L., Chen, Y., Ouyang, W., Bronstein, M.M., and Torr, P.H.S. (2022). Understanding Graph Transformers by Generalized Propagation. arXiv."},{"key":"ref_22","unstructured":"Ramazi, R. (2025). Multi-Modal Data, Deep Learning, Clustering, Predictive Modeling, Type 2 Diabetes, Dementia, and Clustering. [Ph.D. Thesis, University of Delaware]."},{"key":"ref_23","unstructured":"Mahmoudyan, M., and Zeqiri, A. (2021). Time Series Forecasting Using Neural Networks Minimizing Food Waste by Forecasting Demand in Retail Sales. Preprint."},{"key":"ref_24","unstructured":"Kim, S.Y., Wang, S., and Choe, E.K. (2024). Semi-Supervised Graph Representation Learning with Human-Centric Explanation for Predicting Fatty Liver Disease. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Tsolakidis, D., Gymnopoulos, L.P., and Dimitropoulos, K. (2024). Artificial Intelligence and Machine Learning Technologies for Personalized Nutrition: A Review. Informatics, 11.","DOI":"10.3390\/informatics11030062"},{"key":"ref_26","unstructured":"Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 13\u201318). A Simple Framework for Contrastive Learning of Visual Representations. Proceedings of the International Conference on Machine Learning, PMLR, Virtual."},{"key":"ref_27","first-page":"11525","article-title":"Cuts+: High-Dimensional Causal Discovery from Irregular Time-Series","volume":"38","author":"Cheng","year":"2024","journal-title":"Proc. Aaai Conf. Artif. Intell."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"108571","DOI":"10.1016\/j.cmpb.2024.108571","article-title":"Preserving Privacy in Healthcare: A Systematic Review of Deep Learning Approaches for Synthetic Data Generation","volume":"260","author":"Liu","year":"2025","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2896","DOI":"10.1109\/TIP.2025.3564829","article-title":"Variational Bayes Image Restoration with Compressive Autoencoders","volume":"34","author":"Biquard","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Yuan, J., Gao, H., Dai, D., Luo, J., Zhao, L., Zhang, Z., and Zeng, W. (2025). Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention. arXiv.","DOI":"10.18653\/v1\/2025.acl-long.1126"},{"key":"ref_31","unstructured":"Xu, Z., Zhang, L., Yang, S., Etesami, R., Tong, H., Zhang, H., and Han, J. (2024). Ffomaml: GNN-Enhanced Meta-Learning for Peak Period Demand Forecasting with Proxy Data. arXiv."},{"key":"ref_32","unstructured":"Rowan, C., and Doostan, A. (2025). On the Definition and Importance of Interpretability in Scientific Machine Learning. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Startari, A.V. (2025, August 20). Expense Coding Syntax: Misclassification in AI-Powered Corporate ERPs. SSRN. Available online: https:\/\/zenodo.org\/records\/16322760.","DOI":"10.2139\/ssrn.5361952"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s12161-025-02826-7","article-title":"Convolutional Neural Networks for Evaluating Spirulina (Arthrospira spp.) Adulteration Through Digital Images","volume":"18","author":"Paranhos","year":"2025","journal-title":"Food Anal. Methods"},{"key":"ref_35","unstructured":"Litty, A., Okunola, A., and Lima, G. (2025). Automatically Discovering Novel and Efficient Algorithmic Structures Using Deep Learning. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1109\/JBHI.2022.3181823","article-title":"Federated Learning for Privacy Preservation in Smart Healthcare Systems: A Comprehensive Survey","volume":"27","author":"Ali","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_37","first-page":"1210","article-title":"Advances and Open Problems in Federated Learning","volume":"14","author":"Kairouz","year":"2021","journal-title":"Found. Trends\u00ae Mach. Learn."},{"key":"ref_38","unstructured":"Molnar, C. (2025, August 20). Interpretable Machine Learning. Lulu.com, 2020. Published on 21 February 2019. Available online: http:\/\/leanpub.com\/interpretable-machine-learning."},{"key":"ref_39","first-page":"335","article-title":"Research on Interference Recognition Technique Based on Adaptive Multimodal Convolutional Denoising Network","volume":"Volume 13692","author":"Zheng","year":"2015","journal-title":"Proceeding of the Fourth International Conference on Electronics Technology and Artificial Intelligence (ETAI 2025), Harbin, China, 21\u201323 February 2025"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Johari, S., and Singh, P. (2025). Cognitive Intelligence and Big Data: A Symbiotic Approach to Predictive Analytics in Healthcare. 2025 International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), IEEE.","DOI":"10.1109\/IC3ECSBHI63591.2025.10990655"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"043129","DOI":"10.1103\/PhysRevResearch.5.043129","article-title":"Directedness, correlations, and daily cycles in springbok motion: From data via stochastic models to movement prediction","volume":"5","author":"Meyer","year":"2023","journal-title":"Phys. Rev. Res."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"12077","DOI":"10.1038\/s41598-019-48525-2","article-title":"Burst statistics in an early biofilm quorum sensing model: The role of spatial colony-growth heterogeneity","volume":"9","author":"Kindler","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1093\/biomet\/58.1.83","article-title":"Spectra of some self-exciting and mutually exciting point processes","volume":"58","author":"Hawkes","year":"1971","journal-title":"Biometrika"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1103\/PhysRev.36.823","article-title":"On the theory of the Brownian motion","volume":"36","author":"Uhlenbeck","year":"1930","journal-title":"Phys. Rev."},{"key":"ref_45","unstructured":"NielsenIQ (2025, August 20). NielsenIQ Homescan Panel Data. 2025. Chicago, IL, USA. Available online: https:\/\/nielseniq.com."},{"key":"ref_46","unstructured":"U.S. Department of Agriculture (USDA) (2025, August 20). FoodData Central: SR Legacy Release. 2025. Beltsville, MD, USA, Available online: https:\/\/fdc.nal.usda.gov."},{"key":"ref_47","unstructured":"Centers for Disease Control and Prevention (CDC) (2025, August 20). CDC WONDER: Wide-Ranging Online Data for Epidemiologic Research, Available online: https:\/\/wonder.cdc.gov."},{"key":"ref_48","unstructured":"World Health Organization (WHO) (2025, August 20). Global Health Observatory Data Repository. Available online: https:\/\/www.who.int\/data\/gho."},{"key":"ref_49","unstructured":"Google LLC (2025, August 20). Google Trends API (Alpha). Available online: https:\/\/developers.google.com\/search\/blog\/2025\/07\/trends-api."},{"key":"ref_50","unstructured":"(2025, August 20). X (formerly Twitter). Academic Research API. Available online: https:\/\/developer.x.com."},{"key":"ref_51","unstructured":"Centers for Disease Control and Prevention (CDC) (2025, August 20). National Health and Nutrition Examination Survey (NHANES), Available online: https:\/\/www.cdc.gov\/nchs\/nhanes."},{"key":"ref_52","unstructured":"Centers for Disease Control and Prevention (CDC) (2025, August 20). CDC PLACES: Local Data for Better Health, Available online: https:\/\/www.cdc.gov\/places."},{"key":"ref_53","unstructured":"National Centers for Environmental Information (NCEI), National Oceanic and Atmospheric Administration (NOAA) (2025, August 20). Climate Data Online (CDO), Available online: https:\/\/www.ncei.noaa.gov\/cdo-web."},{"key":"ref_54","unstructured":"U.S. Environmental Protection Agency (EPA) (2025, August 20). EPA Open Data Portal, Available online: https:\/\/www.epa.gov\/data."},{"key":"ref_55","unstructured":"American Academy of Allergy, Asthma & Immunology (AAAAI) (2025, August 20). National Allergy Bureau (NAB) Pollen Data. Available online: https:\/\/www.aaaai.org\/global\/nab-pollen-counts."},{"key":"ref_56","unstructured":"UK Biobank (2025, August 20). UK Biobank Genotype and Phenotype Database. Available online: https:\/\/www.ukbiobank.ac.uk."},{"key":"ref_57","unstructured":"American Gut Project (2025, August 20). Microbiome Sequencing Data (EBI Accession ERP012803). Available online: https:\/\/www.ebi.ac.uk\/ena\/browser\/view\/ERP012803."},{"key":"ref_58","unstructured":"Kantar Media (2025, August 20). Advertising and Consumer Panel Data. 2025. London, UK. Available online: https:\/\/www.kantar.com."},{"key":"ref_59","unstructured":"Wesleyan Media Project (2025, August 20). Kantar\/CMAG Advertising Data for Political Research. Available online: https:\/\/mediaproject.wesleyan.edu."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s13040-025-00425-0","article-title":"A Deep Learning Approach for Classifying and Predicting Children\u2019s Nutritional Status in Ethiopia Using LSTM-FC Neural Networks","volume":"18","author":"Begashaw","year":"2025","journal-title":"BioData Min."},{"key":"ref_61","unstructured":"Pareek, P., Mishra, S., Reis, M.J.C.S., and Gupta, N. (2025). An Efficient Approach for Food Demand Forecasting Using an Ensemble Technique and Statistical Analysis. Cognitive Computing and Cyber Physical Systems. IC4S 2024, Springer."},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Barsocchi, P., Naga Srinivasu, P., Kumar Bhoi, A., and Palumbo, F. (2025). Enhancing Patient Data Clustering in Smart Healthcare: A Semisupervised Approach for Person-Centric HealthCare Treatment and Resource Optimization. Enabling Person-Centric Healthcare Using Ambient Assistive Technology, Volume 2, Springer.","DOI":"10.1007\/978-3-031-82516-3"},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"5959","DOI":"10.1038\/s41598-025-88728-4","article-title":"Hybrid Greylag Goose Deep Learning with Layered Sparse Network for Women Nutrition Recommendation During Menstrual Cycle","volume":"15","author":"Logapriya","year":"2025","journal-title":"Sci. Rep."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/3\/156\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T16:15:47Z","timestamp":1772468147000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/3\/156"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,2]]},"references-count":63,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["computers15030156"],"URL":"https:\/\/doi.org\/10.3390\/computers15030156","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,2]]}}}