IoT Based Peatland Ground Level Water Management Using Machine Learning Model

The potential for enormous carbon emissions after fires makes peatlands a serious environmental hazard. Effective management is hampered by the labour intensive and real-time data-poor nature of conventional ground water level (GWL) monitoring in peatlands. issue study addressed issue by proposing an IoT system for real-time monitoring that uses neural network-based GWL prediction. The neural network forecasts GWL based on meteorological factors, giving the responsible party more time to take the necessary steps to lower the danger of fire in peatlands. With a Root Mean Square Error (RMSE) ranging from 3.554 to 4.920, the suggested neural network shows encouraging results and guarantees 99% accuracy within a 14.760 mm range of the real GWL. This research highlights the innovative method of combining neural networks and the Internet of Things for peatland GWL prediction, providing a major breakthrough in real-time monitoring and fire risk reduction techniques. The innovation is its capacity to use basic meteorological information to anticipate GWL in real-time, even in places without the resources for traditional monitoring.