JOURNAL OF IEEE TRANSACTIONS ON ARTIFICIAL INTELLIGENCE, VOL. 00, NO. 0, MONTH 2023 1 Smart Farming: Crop Recommendation using Machine Learning with Challenges and Future Ideas Devendra Dahiphale, Pratik Shinde, Koninika Patil, and Vijay Dahiphale Abstract—Crop analysis and prediction is a rapidly growing field which is vital in optimizing agricultural practices. Crop recommendation is pivotal in agriculture, empowering farmers to make informed decisions about the most suitable crops for their land and climate conditions. Traditionally, this process heavily relied on expert knowledge, which proved time-consuming and labor-intensive. Moreover, considering the projected global population of 9.7 billion by 2050, the need to produce more food sustainably becomes imperative. Machine learning techniques can play a crucial role in effectively automating crop recom- mendations and detecting pests and diseases to enable farmers to optimize their yield from the land while simultaneously maintaining soil fertility and replenishing essential nutrients. This paper analyses the performance of crop recommendation across seven distinct machine-learning algorithms. The proposed system leverages various features, including soil composition and climate data, to accurately predict the most suitable crops for specific locations. This system has the potential to revolutionize crop recommendation, benefiting farmers of all scales by enhancing crop yields, sustainability, and overall profitability. Through ex- tensive evaluation of a comprehensive historical data set, we have achieved near-perfect accuracy by training and testing models the machine learning algorithms with various configurations. We demonstrate accuracy consistently over 95% across all models, with the highest achieved accuracy reaching 99.5%. Impact Statement—This work presents machine-learning mod- els for crop recommendation that achieves near-perfect accuracy. The system leverages various features, including soil compo- sition and climate data, to predict the most suitable crops accurately. This system has the potential to revolutionize crop recommendation, benefiting farmers of all scales by enhancing crop yields, sustainability, and overall profitability. Some of the potential impacts include increased crop yield, improved sustainability, increased profitability, improved decision-making, and avoiding dependency on experts for crop recommendation. We believe that this system has the potential to revolutionize crop recommendations and help to ensure a sustainable food supply for the future. The world population is nearing 8 billion, and we all depend on agriculture for food, so ensuring that our agricultural systems are sustainable and resilient is essential. An end-to-end system can be built using our models, and additionally, farmers’ surveys can be taken for impacts in terms of numbers which is one of the future scopes for this manuscript. Index Terms—Machine Learning, Prediction, Data Analysis, Recommendation, Big Data, Agriculture, Crop, Food, Environ- mental Factors, Agricultural Productivity. Devendra Dahiphale was with the University of Maryland Baltimore County, Baltimore, MD 21250, USA. (e-mail: devendr1@umbc.edu) Pratik Shinde was with the University of Maryland Baltimore County, Baltimore, MD 21250, USA. (e-mail: pratiks1@umbc.edu) Koninika Patil was with the University of Maryland Baltimore County, Baltimore, MD 21250, USA. (e-mail: koni1@umbc.edu) Vijay Dahiphale was with Pune Institute of Computer Technology, Pune, India. (e-mail: vijaydahiphale96@umbc.edu) This paragraph will include the Associate Editor who handled your paper. I. I NTRODUCTION M ACHINE learning [1][2] is a field of study that gives computers the ability to learn without being explicitly programmed, a definition by Arthur Samuel (1959). Machine learning algorithms [3] are trained on large amounts of data to make predictions or decisions. Agriculture, being a major sector worldwide, requires farm- ers to cultivate profitable and sustainable crops. Not choosing the right crop can have a significant impact on crop yield, leading to decreased productivity and potential financial losses for farmers. When farmers fail to consider crucial factors such as climate suitability, soil conditions, and market demand, the chosen crops may struggle to thrive and achieve their full yield potential. Unsuitable crops may suffer from inadequate adaptation to the local climate, resulting in poor growth, in- creased vulnerability to pests and diseases, and reduced overall yield. Moreover, crops that do not align with market demand may face difficulties in finding buyers or fetching favorable prices, further exacerbating the economic impact on farmers. By leveraging machine learning-based crop recommendation systems, farmers can mitigate these challenges and make informed decisions to maximize crop yield and ensure long- term agricultural viability. Machine learning and agricultural data converge to revolu- tionize how farmers understand and optimize their practices. With the increasing availability of data from sources such as weather stations, satellites, sensors, and farm equipment, machine learning algorithms can analyze vast amounts of information and extract valuable insights. These algorithms can uncover complex patterns, correlations, and predictive models that were previously hidden within the data. By combining machine learning techniques with agricultural data, farmers gain the ability to make data-driven decisions, ranging from crop selection and irrigation management to pest control and yield prediction. This integration empowers farmers to achieve higher efficiency, resource optimization, and sustain- able practices, ultimately leading to improved productivity and profitability in the agricultural sector. Crop recommendation systems can be used to analyze a variety of data, such as weather data, soil data, and market data. This data can be used to train machine learning models to predict which crops will likely be successful in a given lo- cation. Crop recommendation systems can also inform farmers about the best practices for growing specific crops. The development of crop recommendation systems using machine learning has the potential to improve the productivity and sustainability of agriculture. By helping farmers to choose