CAMEL: An Intelligent Computational Model for Agro-Meteorological Data

Weather plays an important role in agriculture. This calls for reliable weather information, which in turn helps farmers make management decisions about their crops. In this paper, we propose an intelligent computational model for agro-meteorological data (CAMEL). The model serves three purposes. First, it effectively captures important information about large amounts of data collected from various weather stations distributed in a wide geographic expanse. Second, the proposed model learns from historical data and predicts future trends. This helps us obtain accurate weather forecasts. Third, through the prediction of weather trends, CAMEL gives us a better understanding of agro-meteorological data. When we compare the predicted results with the observed data, any significant difference between them may be an indication of equipment malfunction or other problems. In this way, CAMEL helps us detect abnormal data and facilitates in guarding against potential sources of error. Consequently, well-functioning equipment and accurate weather data help farmers make wise crop management decisions. Experimental results on real-life datasets show the effectiveness of our proposed intelligent computational model for agro-meteorological data.