{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T13:36:04Z","timestamp":1785418564881,"version":"3.56.0"},"reference-count":56,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T00:00:00Z","timestamp":1776988800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Innovational Fund for Scientific and Technological Personnel of Hainan Province","award":["KJRC2025B20"],"award-info":[{"award-number":["KJRC2025B20"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62562028"],"award-info":[{"award-number":["62562028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["62562028"],"award-info":[{"award-number":["62562028"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>To address statistical heterogeneity and update-level privacy risks in federated learning for geospatial data, this paper proposes a hierarchically decoupled collaborative framework that integrates client-side privacy perturbation with server-side consistency-aware aggregation, while incorporating governance as a system-level support module. Under strong non-IID conditions, the proposed soft-weight aggregation strategy mitigates update mismatch and improves convergence stability without hard filtering legitimate but distributionally shifted client contributions. Meanwhile, the risk-aware perturbation mechanism adaptively adjusts clipping and noise strength across clients to better balance privacy protection and model utility. An on-chain governance and off-chain training coordination mechanism is further introduced to support auditable and traceable collaboration without interfering with the main optimization process. Experimental results on EuroSAT_RGB with ResNet-18 show that the proposed design achieves more stable training and better overall performance than the compared baselines, especially under severe heterogeneity. These findings highlight the value of jointly considering privacy-aware perturbation and consistency-aware aggregation for improving training stability and preserving utility in geospatial federated learning under statistically heterogeneous settings.<\/jats:p>","DOI":"10.3390\/info17050404","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T14:28:23Z","timestamp":1777040903000},"page":"404","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Privacy-Enhanced Stable Federated Learning for Statistically Heterogeneous Geospatial Data"],"prefix":"10.3390","volume":"17","author":[{"given":"Yiqi","family":"Sun","sequence":"first","affiliation":[{"name":"School of Cyberspace Security (School of Cryptography), Hainan University, Haikou 570228, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keer","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security (School of Cryptography), Hainan University, Haikou 570228, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security (School of Cryptography), Hainan University, Haikou 570228, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hezheng","family":"Lan","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security (School of Cryptography), Hainan University, Haikou 570228, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6564-1568","authenticated-orcid":false,"given":"Hong","family":"Lei","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security (School of Cryptography), Hainan University, Haikou 570228, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Dritsas, E., and Trigka, M. (2025). Remote sensing and geospatial analysis in the big data era: A survey. Remote Sens., 17.","DOI":"10.3390\/rs17030550"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zeng, F., Pang, C., and Tang, H. (2024). Sensors on internet of things systems for the sustainable development of smart cities: A systematic literature review. Sensors, 24.","DOI":"10.3390\/s24072074"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Kumar, D., Banerjee, S., Sarangi, S.K., and Singh, S.P. (2025). Revolutionizing Environmental Hazard Management with Remote Sensing and GIS. Environment and Public Health: Insights Towards Theory, Evidences and Sustainable Solutions, Springer Nature Switzerland.","DOI":"10.1007\/978-3-031-99770-9_22"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1109\/MGRS.2025.3576766","article-title":"Foundation models for remote sensing and earth observation: A survey","volume":"13","author":"Xiao","year":"2025","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1111\/area.12888","article-title":"Privacy challenges in geodata and open data","volume":"55","author":"Solymosi","year":"2023","journal-title":"Area"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"100974","DOI":"10.1016\/j.patter.2024.100974","article-title":"Privacy preservation for federated learning in health care","volume":"5","author":"Pati","year":"2024","journal-title":"Patterns"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"128019","DOI":"10.1016\/j.neucom.2024.128019","article-title":"Recent advances on federated learning: A systematic survey","volume":"597","author":"Liu","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Shi, Z., Gong, D., and Yan, X. (2024). A Comprehensive Review of Federated Learning: Concepts, Aggregation Methods, Applications, and Challenges. International Conference on Logistics, Informatics and Service Sciences, Springer Nature Singapore.","DOI":"10.1007\/978-981-96-9697-0_77"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e38137","DOI":"10.1016\/j.heliyon.2024.e38137","article-title":"Federated learning: Overview, strategies, applications, tools and future directions","volume":"10","author":"Yurdem","year":"2024","journal-title":"Heliyon"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Alterkawi, L., and Dib, F.K. (2025). Federated Learning for Smart Cities: A Thematic Review of Challenges and Approaches. Future Internet, 17.","DOI":"10.3390\/fi17120545"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"124583","DOI":"10.1016\/j.eswa.2024.124583","article-title":"Federated learning meets remote sensing","volume":"255","author":"Paoletti","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_12","first-page":"1","article-title":"Heterogeneous federated learning: State-of-the-art and research challenges","volume":"56","author":"Ye","year":"2023","journal-title":"Acm Comput. Surv."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1007\/s10586-025-05250-y","article-title":"Harmony in federated learning: A comprehensive review of techniques to tackle heterogeneity and non-IID data","volume":"28","author":"Karami","year":"2025","journal-title":"Clust. Comput."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Cha, N., and Chang, L. (2025). Addressing Non-IID with Data Quantity Skew in Federated Learning. Information, 16.","DOI":"10.3390\/info16100861"},{"key":"ref_15","unstructured":"Bao, W., Wu, J., and He, J. (2024). BOBA: Byzantine-robust federated learning with label skewness. International Conference on Artificial Intelligence and Statistics, PMLR."},{"key":"ref_16","unstructured":"Zhang, X., Chen, X., Hong, M., Wu, Z.S., and Yi, J. (2022). Understanding clipping for federated learning: Convergence and client-level differential privacy. International Conference on Machine Learning, ICML."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.1007\/s10462-023-10550-z","article-title":"Gradient leakage attacks in federated learning","volume":"56","author":"Gong","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"ref_18","unstructured":"Du, J., Hu, J., Wang, Z., Sun, P., Gong, N.Z., Ren, K., and Chen, C. (2025, January 13\u201315). SoK: On gradient leakage in federated learning. Proceedings of the 34th USENIX Conference on Security Symposium, Seattle, WA, USA."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chang, Z., Hu, J., Pang, X., Du, J., Chen, Y., and Ren, K. (2024). Breaking secure aggregation: Label leakage from aggregated gradients in federated learning. IEEE INFOCOM 2024\u2014IEEE Conference on Computer Communications, IEEE.","DOI":"10.1109\/INFOCOM52122.2024.10621090"},{"key":"ref_20","first-page":"101052","article-title":"A thorough assessment of the non-IID data impact in federated learning","volume":"50","author":"Hassanzadeh","year":"2025","journal-title":"J. Ind. Inf. Integr."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1449","DOI":"10.1109\/TSC.2023.3336980","article-title":"Decentralized and incentivized federated learning: A blockchain-enabled framework utilising compressed soft-labels and peer consistency","volume":"17","author":"Witt","year":"2023","journal-title":"IEEE Trans. Serv. Comput."},{"key":"ref_22","first-page":"5125","article-title":"A federated learning framework with blockchain-based auditable participant selection","volume":"79","author":"Huang","year":"2024","journal-title":"Comput. Mater. Contin."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"103814","DOI":"10.1016\/j.jnca.2023.103814","article-title":"VDFChain: Secure and verifiable decentralized federated learning via committee-based blockchain","volume":"223","author":"Zhou","year":"2024","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Ben Youssef, B., Alhmidi, L., Bazi, Y., and Zuair, M. (2024). Federated learning approach for remote sensing scene classification. Remote Sens., 16.","DOI":"10.3390\/rs16122194"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"922","DOI":"10.1007\/s11036-024-02352-6","article-title":"Cost-efficient hierarchical federated edge learning for satellite-terrestrial Internet of Things","volume":"29","author":"Pei","year":"2024","journal-title":"Mob. Netw. Appl."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"113007","DOI":"10.1016\/j.knosys.2025.113007","article-title":"Heterogeneity-aware pruning framework for personalized federated learning in remote sensing scene classification","volume":"311","author":"Hu","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"ref_27","first-page":"1","article-title":"Fed-RSSC: A Semi-Decentralized Federated Framework for Remote Sensing Scene Classification","volume":"22","author":"Jin","year":"2025","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1109\/MGRS.2025.3556532","article-title":"FedRSCLIP: Federated learning for remote sensing scene classification using vision-language models","volume":"13","author":"Lin","year":"2025","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Tan, J., Zhang, C., Dang, B., and Li, Y. (2025, January 19\u201323). Towards Privacy-preserved Pre-training of Remote Sensing Foundation Models with Federated Mutual-guidance Learning. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Honolulu, HI, USA.","DOI":"10.1109\/ICCV51701.2025.00176"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"5936","DOI":"10.1109\/TIFS.2025.3576008","article-title":"EARVP: Efficient aggregation for federated learning with robustness, verifiability, and privacy","volume":"20","author":"Yan","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"12635","DOI":"10.1109\/TMC.2024.3417930","article-title":"Does differential privacy really protect federated learning from gradient leakage attacks?","volume":"23","author":"Hu","year":"2024","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zheng, L., Cao, Y., Yoshikawa, M., Shen, Y., Rashed, E.A., Taura, K., Hanaoka, S., and Zhang, T. (2025). Sensitivity-aware differential privacy for federated medical imaging. Sensors, 25.","DOI":"10.3390\/s25092847"},{"key":"ref_33","unstructured":"Kianidehkordi, S., Kulkarni, N., Dziedzic, A., Draper, S., and Boenisch, F. (2025). Differentially Private Federated Learning with Time-Adaptive Privacy Spending. International Conference on Learning Representations (ICLR 2025), ICLR."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Liu, J., Zeng, Y., Wang, Z., Zhang, W., and Tong, Y. (2026). Differentially Private Federated Learning with Adaptive Clipping Thresholds. Future Internet, 18.","DOI":"10.3390\/fi18030148"},{"key":"ref_35","unstructured":"Yin, D., Chen, Y., Kannan, R., and Bartlett, P. (2018). Byzantine-robust distributed learning: Towards optimal statistical rates. International Conference on Machine Learning, PMLR."},{"key":"ref_36","unstructured":"Blanchard, P., El Mhamdi, E.M., Guerraoui, R., and Stainer, J. (2017). Machine learning with adversaries: Byzantine tolerant gradient descent. Advances in Neural Information Processing Systems, Neural Information Processing Systems Foundation, Inc. (NeurIPS)."},{"key":"ref_37","unstructured":"Karimireddy, S.P., Kale, S., Mohri, M., Reddi, S., Stich, S., and Suresh, A.T. (2020). Scaffold: Stochastic controlled averaging for federated learning. International Conference on Machine Learning, PMLR."},{"key":"ref_38","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref_39","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume":"Volume 33","author":"Wang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1136","DOI":"10.1007\/s11227-025-07616-w","article-title":"RHFL: A robust method to defend against poisoning attacks for heterogeneous hierarchical federated learning","volume":"81","author":"Zhao","year":"2025","journal-title":"J. Supercomput."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"100182","DOI":"10.1016\/j.neuri.2024.100182","article-title":"KL-FedDis: A federated learning approach with distribution information sharing using Kullback-Leibler divergence for non-IID data","volume":"5","author":"Rahad","year":"2025","journal-title":"Neurosci. Inform."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"670","DOI":"10.26599\/TST.2023.9010091","article-title":"Optimizing data distributions based on Jensen-Shannon divergence for federated learning","volume":"30","author":"Hu","year":"2024","journal-title":"Tsinghua Sci. Technol."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1007\/s00778-024-00839-y","article-title":"Refiner: A reliable and efficient incentive-driven federated learning system powered by blockchain","volume":"33","author":"Lin","year":"2024","journal-title":"VLDB J."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"103163","DOI":"10.1016\/j.sysarc.2024.103163","article-title":"BFL-SA: Blockchain-based federated learning via enhanced secure aggregation","volume":"152","author":"Liu","year":"2024","journal-title":"J. Syst. Archit."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Ren, S., Kim, E., and Lee, C. (2024). A scalable blockchain-enabled federated learning architecture for edge computing. PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0308991"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"9240","DOI":"10.1109\/TMC.2024.3361089","article-title":"A blockchain-empowered incentive mechanism for cross-silo federated learning","volume":"23","author":"Tang","year":"2024","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Zeng, H., Yang, A., Weng, J., Chen, M.R., Xiao, F., Liu, Y., and Yao, Y. (2024). Enabling privacy-preserving and publicly auditable federated learning. ICC 2024-IEEE International Conference on Communications, IEEE.","DOI":"10.1109\/ICC51166.2024.10622406"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"104165","DOI":"10.1016\/j.jnca.2025.104165","article-title":"CBRFL: A framework for Committee-based Byzantine-Resilient Federated Learning","volume":"238","author":"Xu","year":"2025","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Wu, B., and Seneviratne, O. (2025). Blockchain-based Framework for Scalable and Incentivized Federated Learning. Companion Proceedings of the ACM on Web Conference 2025, Association for Computing Machinery.","DOI":"10.1145\/3701716.3717649"},{"key":"ref_50","unstructured":"Cover, T.M. (1999). Elements of Information Theory, John Wiley & Sons."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"130977","DOI":"10.1016\/j.eswa.2025.130977","article-title":"FedCC: Federated Cluster-Aware Contrastive Learning with Adaptive Differential Privacy under non-IID Settings","volume":"307","author":"Yuan","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_52","unstructured":"Fabric, H. (2023). Hyperledger Fabric Documentation, The Linux Foundation."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"16440","DOI":"10.1109\/ACCESS.2020.2967218","article-title":"Solutions to scalability of blockchain: A survey","volume":"8","author":"Zhou","year":"2020","journal-title":"IEEE Access"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Gervais, A., Karame, G.O., W\u00fcst, K., Glykantzis, V., Ritzdorf, H., and Capkun, S. (2016, January 24\u201328). On the security and performance of proof of work blockchains. Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, Vienna, Austria.","DOI":"10.1145\/2976749.2978341"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Atzei, N., Bartoletti, M., and Cimoli, T. (2017). A survey of attacks on ethereum smart contracts (SoK). International Conference on Principles of Security and Trust, Springer.","DOI":"10.1007\/978-3-662-54455-6_8"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","article-title":"EuroSAT: A novel dataset and deep learning benchmark for land use and land cover classification","volume":"12","author":"Helber","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/5\/404\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T04:11:37Z","timestamp":1778645497000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/5\/404"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,24]]},"references-count":56,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["info17050404"],"URL":"https:\/\/doi.org\/10.3390\/info17050404","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,24]]}}}