Crop Recommendation System using Machine Learning

Agriculture plays a big role in ensuring global food security and sustainability. To optimize crop yields, it is essential to understand the soil and weather conditions of a farm. In this study, we developed a Crop Selection System that leverages the IoT and ML, specifically the Random Forest algorithm, to assist farmers of Rwanda in choosing the most suitable crops for their piece of land. The system makes recommendations based on measurements of nitrogen, phosphorus, potassium, pH, humidity, rainfall, and temperature before cultivation begins. Realtime field data was gathered using IoT sensors deployed in farm areas to collect soil and environmental information. Our device utilized soil sensors to measure nitrogen, soil pH, humidity, phosphorus, temperature, and potassium. The NodeMCU microcontroller preprocessed the data and uploaded it to a cloud database. The data collection took place in Gicumbi District, and the collected samples were analyzed using our crop selection model. The model was developed using the Random Forest algorithm to evaluate soil compatibility and rank the crops based on their probability of successful growth. By training the model with a dataset of crops' ecological requirements, we achieved an accuracy of 96%. We then tested the model with newly collected data from the field. Over a period of seven days, the model's predictions indicated that potatoes had the highest growing probability at 56%, followed by beans at 43%, carrots at 33%, tomatoes at 33%, and rice at 17%. This data-driven approach significantly enhances farmers' decision-making by enabling them to make informed choices about crop selection. This technology can boost agricultural productivity while reducing unnecessary costs, such as excessive fertilizer use, by ensuring crops are cultivated based on the available ecological conditions. The system helps farmers assess nutrient levels and implement corrective measures to restore soil fertility. This method advances precision agriculture and contributes to the overall modernization of farming practices.

Indonesian Journal of Electrical Engineering and Computer Science, 2022

Agriculture is the major occupation in India. The development of India is in the hands of farmers. Farmers are said to be our nation's backbone, so there is a need to support our farmers technologically so that the difficulties of traditional agricultural practices would be overcome and also there will be positive impact on the yield, harvest, healthy crop output and the income of the farmers. Farmer needs awareness about his soil and the methods to improve his soil to grow the healthy crops. We propose an approach which involves deep learning and some IoT features to help our farmers. Soil parameters such as nitrogen, phosphorous, potassium (NPK), pH, organic carbon, moisture content and few more things are considered for predicting the fertility of the soil and also to predict the right crops to be grown and nutrition required for it. We have developed a deep neural network model to predict the crop which can be suitably grown in the soil. We have also implemented the other machine learning classifiers on the same collected dataset to test the accuracies of each classifier and our deep neural network model.

International journal of engineering technology and management sciences, 2022

In traditional ways, understanding the situation of the crop is not that much easy to detect and prevent the diseases in the crop. The availability of skill full farmers and manpower is less. Farmers still have insufficient knowledge and awareness of available latest technologies to facilitate fast and effective management of crops, parameters like soil health, effect of weather condition, water management, species management, yield prediction, crop recommendation, use of fertilizers etc. Now a days Machine learning model is widely used to predict the accuracy of the result. This article aims to provide information of different machine learning approaches proposed to study soil health and crop predictions with its advantages in agriculture sector of India in last decade.

International Journal for Research in Applied Science and Engineering Technology

Agriculture plays the main role in a country's economic development. In the recent agricultural practices, the variation in climatic phenomena affects the weather conditions in different regions and based on that the soil characteristics may also vary. This influences the crop to be sown for getting a better yield. In agriculture with the advent of new technology, farming practices are now converted into precision farming. It includes the use of modern technology such as the Internet of Things (IoT) and Data Analytics for optimal crop health and crop productivity. This improves the growth rate of the crops, but the problem among farmers is they are not choosing the right crop at right time. Although several algorithms are there the Deep Learning based Artificial Neural Networks is found to be more effective for prediction and modeling. The algorithm accuracy and the prediction level vary based on the type of parameters chosen. The proposed system helps the farmers by gathering information about the basic characteristics of their soil such as soil moisture level, temperature, pH, and humidity. In addition, the sensor provides valuable information about crops such as sowing time, fertilizer suggestion and real-time monitoring. These data can be collected using sensors and with the help of that data, the Deep Learning technique such as Deep Neural Network (DNN) which is an Artificial Neural Network (ANN) can be applied to end up with valuable decision making.

International Journal of Progressive Research in Science and Engineering, 2021

Soils are astounding mixes of minerals, water, air, regular matter, and incalculable living creatures that are the spoiling gets by from once living things. Soils fill in as media for improvement of a wide scope of plants we can say soil is a significant element of farming. There are a couple of kinds of soils and every sort of soil can have different sorts of features and different kinds of yields create on different kinds of soils. We should realize which sort of our dirt is go better in our dirt. We can apply AI techniques to bunch soil and to expect the yield sensible.

Journal of Nanomaterials

The available nutrient status of the mulberry gardens in the districts of Tamil Nadu is analyzed and evaluated to find the status. In this work, the soil is classified based on the test report to a number of features with fertility indices for boron (B), organic carbon (OC), potassium (K), phosphorus (P), and available boron (B), along with the parameter soil reaction (pH). A total of 10 steps are used for cross-validation purposes wherein in every step, the data involves 10% for validation and the remaining for training data. A fast learning classification methodology known as extreme learning method (ELM) is trained using the data to identify the micronutrients present in the soil. Activation functions such as hard limit, triangular basis, hyperbolic tangent, sine-squared, and Gaussian radial basis are used to optimize the methodology. Based on the analysis performed, the nutrients are classified and the optimal soil conditions are proposed for different regions that are analyzed....

International journal of health sciences

Agriculture is the important part of any developing country. As population increases the food requirement also be increases so the traditional farming not sufficient to fulfill the requirement of food. The development of industries, decreases in land space, insufficient rainfall, chemicals used in farming and peoples are moving towards the urban cities are the challenges of the agricultural field. So we have to use another source of food which we called as hydroponics. In hydroponics we can developed our plant by supplying the nutrients through water without use of soil. In this study we had used the applicability of machine learning algorithm like support vector regression(SVR), Linear Regression, Lasso Regression, Decision Tree(DT), Ridge regression and Random forest to find the crop growth accuracy from the result we found that random forest has given the highest accuracy 95% and the performance are evaluated on various model like Decision Tree Regression having better performanc...