| | S. no. | Supervised models used | Research findings | References |
| | 1. | Decision tree, logistic regression, KNN, SVM, Naïve Bayes, and random forest | This research utilized six traditional classifiers—decision tree (DT), logistic regression (LR), K-nearest neighbor (KNN), support vector machine (SVM), Naïve Bayes (NB), and random forest (RF)—as well as an ensemble of six classifiers to build the machine learning model. According to the study, classification accuracy using DT, KNN, SVM, and RF is good. With six ensemble classifiers, the model also discovers the greatest accuracy of 100%. The System Usability Scale (SUS), which measures user satisfaction among frequent users, is also provided for the study. The suggested system’s SUS score is 82% | [30] |
| | 2. | SVM, random forest, and Naïve Bayes | The smart irrigation system described in this article makes use of the cloud and the Internet of Things. In this framework, machine learning algorithms were used to predict how much fresh water would be needed to develop a crop. Thus, a sizable volume of fresh water is conserved. The use of intelligent irrigation will alter the agriculture industry. SVM’s accuracy result is greater than 80%; however, random forest and Naïve Bayes accuracy scores are both less than 77.5% | [13] |
| | 3. | SVM, KNN, and ANN | The study forecasts irrigation needs using a database compiled from multiple sensors, utilizing data from various sensors. Accuracy: KNN 91%, SVM 87%, and ANN 96.87% | [31] |
| | 4. | KNN, SVM LR, NB, and NN | This research presents a machine learning-based irrigation strategy for smart agriculture, utilizing sensors like soil humidity, temperature, and rain. The node-RED platform and MongoDB are used to collect data, with K-nearest neighbors achieving 98.3% accuracy and 0.12 root mean square error. A web application visualizes and supervises the environment, combining sensor data, and model predictions | [12] |
| | 5. | KNN, SVM, GNB, and ANN | The suggested method encourages efficient irrigation by conserving irrigation water while maintaining crop output. We assess the accuracy of three machine learning techniques for determining ET0: Gaussian Naïve Bays (GNB), K-nearest neighbor (KNN), support vector machine (SVM), and artificial neural network (ANN). It has been demonstrated that KNN is more accurate than SVM and GNB models, with 92% accuracy, high precision, recall, and f-measure | [32] |
| | 6. | LR, LDA, KNN, CART, NB, and SVM | The paper describes an intelligent system for the Internet of Things, LoRa-based wireless sensor networks, and machine learning for scheduling and monitoring precise irrigation. The technology forecasts crop water needs based on soil and meteorological variables. There were six different machine learning methods employed, with the linear discriminant analysis technique having the highest prediction accuracy (91.25%). The system’s capabilities enable efficient irrigation scheduling and monitoring of crop water requirements | [33] |
| | 7. | SVM, random forest, and logistic regression | This article proposes a methodology for detecting and categorizing unauthorized access to Internet of Things (IoT) networks in agricultural regions. The precision of random forest is 85%, while the precision of logistic regression is 78%. On the other hand, SVM has an accuracy above 98% | [34] |
| | 8. | KNN | Smart irrigation methods are developed to meet global sweet water needs, ensuring frugal water consumption. A professional technique employing ontology and sensor data values determines 50% of the choice, and sensor data values are used for the other 50%. A machine learning algorithm (KNN) that combines the sensor data and ontology determines the final decision | [35] |
| | 9. | KNN | The article presents a smart irrigation system using wireless sensor networks, drip techniques, and https://Thingspeak.com, an open-source cloud computing platform. The system uses online resources like weather predictions and soil tests to decide when to irrigate crops. The system achieves 89% accuracy, a 10% misclassification rate, 79% sensitivity, 93% specificity, and 81% precision in threshold metrics classification evaluation. The system’s 97% and 98% prediction accuracy indicate reliable and efficient irrigation and water resource management, potentially boosting agricultural production in rural areas | [36] |
|
|
