Analysis of Resolving Efficient Dominating Set and Its Application Scheme in Multi-Step Time Series Forecasting of pH and Soil Moisture in Horizontal Farming

This research focuses on the analyzing the Resolving Efficient Dominating Set (REDS) and its application scheme in horizontal farming using the Spatial Temporal Graph Neural Network (STGNN). Soil moisture and pH are crucial factors that affect the growth and yield, as they directly impact productivity and plant health. In cases where soil moisture and pH are lacking, various types of companion planting need to be watered. In such planting systems, a central role is needed to monitor soil moisture and pH levels effectively. The placement of operators in this system requires the application of mathematical concepts, specifically graph theory. In this study, we explore graph theory, particularly the Resolving Efficient Dominating Set. This involves ensuring that each vertex is dominated by exactly one vertex in D, with no adjacent with another vertex, and the representation of vertex concerning is not the same. To effectively address this issue, including soil moisture and pH data, is required to predict future soil moisture and pH values in companion farming. Spatial Temporal Graph Neural Network (STGNN) technique proves to be useful in solving the problem of soil moisture and pH by understanding and modeling multi-step time series data. This technique aids in effectively managing and optimizing horizontal farming.