Crop-Recommendation in Spatial Clusters Using Meta-Heuristics and Machine Learning Techniques

The crop is the baseline of the Indian economy. To ensure the actual variances of the crops, we need to analyze and further predict the best crop suitable for every spatial feature vector. In order to analyze the dataset, the authors in this paper implemented several machine learning and deep learning techniques upon which the predictions can be assumed. The authors in this paper analysed the meta-heuristic approaches such as particle swarm optimization, cuckoo search, ant colony optimization and in the presence of several factors, they also incorporated the machine learning techniques finding the spatial clusters of crops available to the farmers performing the agriculture on the land. The feature variables extracted from the standard dataset used in this project are Nitrogen, Potassium, Phosphorus, Temperature, Rainfall, and Humidity in the soil. The features are mapped using cuckoo search. The most appropriate features are then selected using Particle Swarm Optimization (PSO). These features are mapped using many machine language algorithms such as KNN (K-Nearest Neighbours) and Random Forest Optimization to provide a single class output. The results obtained are provided to deep learning neural network architecture to obtain multiclass output. The proposed model gives us an accuracy of 98.30% that is promising and higher than all the other algorithms used in the research.