Federated learning (FL) is emerging as a pivotal paradigm for environmental monitoring, enabling decentralized model training across edge devices without exposing raw data. This review provides the first structured synthesis of 361 peer-reviewed studies, offering a comprehensive overview of how FL has been implemented across environmental domains such as air and water quality, climate modeling, smart agriculture, and biodiversity assessment. We further provide comparative insights into model architectures, energy-aware strategies, and edge-device trade-offs, elucidating how system design choices influence model stability, scalability, and sustainability. The analysis traces the technological evolution of FL from communication-efficient prototypes to robust, context-aware deployments that integrate domain knowledge, physical modeling, and ethical considerations. Persistent challenges remain, including data heterogeneity, limited benchmarking, and inequitable access to computational infrastructure. Addressing these requires advances in hybrid physics–AI frameworks, privacy-preserving sensing, and participatory governance. Overall, this review positions FL not merely as a technical mechanism but as a socio-technical shift—one that aligns distributed intelligence with the complexity, uncertainty, and urgency of contemporary environmental science.

The article presents the issues related to the operation and modelling of the ship main propulsion steam boiler. Such objects are used widely in seagoing ships especially the very large crude oil carriers as a main propulsion turbine feed. The advantages of such along with simple construction thus great reliability make oil feed boilers an excellent source of power for chosen type of the large ships. It must be pointed out that a lot of research work was done in the previous years regarding automatic control of boiler automation but since then this technology was not in the focus of the researchers. In the future the fossil fuels will become less important than they are now, but the control techniques of boilers would eventually change due to different fuel parameters therefore, development of such is necessary. The article presents the results of research collected in real ship boilers during their operation and then, based on the results, a digital model of such an object was created. This model was implemented into Hardware-In-Loop which is the initial step for preparing the full model (including sensors etc.) of a steam heated boiler. Theoretical background along with chosen simulation and experimental results of control implemented into HIL were presented to validate assumptions...

This article presents the issues related to the operation and modelling of a ship’s main propulsion steam boiler. Such objects are used widely in seagoing ships, especially very large crude oil carriers, as a main propulsion turbine feed. The advantages, along with the simple construction, thus greatly improve reliability making oil feed boilers an excellent source of power for the chosen types of large ships. It is worth mentioning that a vast part of the research work was performed in previous years regarding automatic control of boiler automation, but, since then, this technology has not been the focus of the researchers. Due to the fact that there is little information available on algorithms for controlling ship boilers, in the presented article, the authors created a unique solution for the control system of a propulsion boiler. The proposed control algorithm takes into account the operating parameters of the ship and allows for quick implementation in a simulation system working in a hardware loop, which can be used for quick testing of solutions for boiler systems fed with alternative fuels. In the future, fossil fuels will become less important than they are now, but the control techniques of boilers will eventually change due to different fuel parameters and, therefore, the development of such boilers is necessary. This article presents the results of research collected in real ship boilers during their operation and, based on the results, a digital model of such an object along with the necessary controls was created. This model was implemented into Hardware-In-Loop, which is the initial step for preparing the full model (including sensors, etc.) of a steam-heated boiler. The theoretical background, along with the chosen simulation and experimental results of control implemented into HIL, are presented to validate assumptions.