The agricultural sector has become an important income source for our country. In terms of nutrient absorption, plant diseases affecting the agricultural yield are creating a great hazard. In agriculture, recognizing infectious plants seems challenging due to the premise of the needed infrastructure. To prevent the spread of diseases, the identification of infectious leaves in the plant is observed to be a necessary step. This work aims to propose a machine learning technique on the ANN method for plant diseases identification and classification. This paper proposes a novel hybrid algorithm, called Black Widow Optimization Algorithm with Mayfly Optimization Algorithm (BWO-MA), for solving global optimization problems. In this paper, a BWO-MA with Artificial Neural Networks (ANN) based diagnostic model for earlier diagnosis of plant diseases is developed. Comparison has been done with existing machine learning methods with the proposed BWO-MA-based ANN architecture to accommodate greater performance. The comprehensive analysis showed that our proposal achieved splendid state-of-the-art performance. 

Timely diagnosis of plant disease is important to get better crop yields. Infected plants can cause significant financial losses to farmers by lowering crop yields. It is extremely desirable to detect early signs and symptoms of plant diseases in a nation like India, where agriculture supports the majority of the population. More accurate and faster plant disease detection might assist in lowering the damage. With tremendous improvements and advancements in deep learning, the effectiveness and precision of plant disease detection and identification systems may be improved. The goal of this study is to discover leaf illnesses found in tomato crops and reduce the financial losses caused by the diseases. We have implemented transfer learning using a pre-trained Squeeze Net Model to detect and classify tomato leaf diseases. Our model can automatically detect 9 types of deadly diseases that are very common in tomato crops. We have acquired 10 classes (one healthy leaf class and 9 diseased leaf classes) consisting of 16,012 tomato leaf samples from a benchmarked Plant Village dataset to train and validate the suggested method. On the public dataset, the class-wise classification precision rate varies from 77.9% to 99.6%, and the overall classification accuracy of the suggested model is observed as 93.1% which is a significant enhancement in performance over previous tomato disease detection techniques. 

Pearl millet is a staple food crop in areas with drought, low soil fertility, and higher temperatures. Fifty percent is the share of pearl millet in global millet production. Numerous types of diseases like Blast, Rust, Bacterial blight, etc., are targeting the leaves of the pearl millet crop at an alarming rate, resulting in reduced yield and poor production quality. Every disease could have distinctive remedies, so, wrong detection can result in incorrect corrective actions. Automatic detection of crop fitness with the use of images enables taking well-timed action to improve yield and in the meantime bring down input charges. Deep learning techniques, especially convolutional neural networks (CNN), have made huge progress in image processing these days. CNNs have been used in identifying and classifying different diseases across many crops. We lack any such work in the pearl millet crop. So, to detect pearl millet crop diseases with great confidence, we used CNN to construct a model in this paper. Neural network models use automatic function retrieval to help in classify the input image into the respective disease classes. Our model outcomes are very encouraging, as we realized an accuracy of 98.08% by classifying images of pearl millet leaves into two different categories namely: Rust and Blast.

The agriculture sector plays a vital role in the Indian Economy and is known as one of the key areas where automation is emerging to enable farmers to increase the yield, prevent damage to the crop, reduce harvesting cost, etc. Artificial Intelligence (AI) offers a large number of direct applications across various sectors and it can bring a paradigm shift in the Indian farming sector. According to the report of the United Nations, the land area for cultivation will be 4% by the year 2050 so smart farming processes are the need of the hour and AI can help in finding solutions to increase the yield of crops and ensure food security. The chapter focuses on the role of solarpowered robots in the agriculture sector with the application of computer vision which is capable of recognizing the physical properties of vegetables and helps in monitoring the yield. We analyse a vegetable image data set with mass and dimension values collected using a computer vision system and accurate measuring devices. After successful detection and instance-wise segmentation, we extract the real-world dimensions of the selected vegetable. After monitoring the health of vegetables, the robot shares the profile through IoT in real-time and thus with low labour cost and without exhaustive search, the crop can be prevented from damage by weeds which can be identified at an early stage. Initial evaluation of the developed prototype exhibited a noteworthy potential of this system in the area of effective control of weeds and crop damage and assisting in harvesting. 

Preventing wild animal attacks in fields is a highly challenging task for farmers and field holders, especially during nighttime. Continuous monitoring is difficult to maintain consistently. Therefore, we have designed an Intrusion Detection System based on the Internet of Things (IoT). Our system utilizes the ESP8266 as its central component, allowing for the implementation of an automated solution to repel animals from fields without human intervention. Various devices, such as hooters, flashlights with day-night vision cameras, and AI algorithms, are incorporated to detect and differentiate animals from humans. Additionally, mobile applications provide a convenient means to remotely monitor the system's actions from home.

Weather forecast is of prime attention of the researchers working in the smart agriculture domain. In India, approximately 55% of the total crops are dependent on weather (monsoon season). An accurate weather forecast model requires abundant data to get the most accurate predictions. However, the weather forecast is a key area of research and is always challenging from historical data. Hence, the current system used for weather forecasting is an amalgamation of forecasting models, opinions, and information trends, and specific patterns. This work presents the application of the linear regression model and polynomial regression model for weather forecasting; like a scheme to forecast rainfall, and precipitation using historical weather data. The sample weather dataset covers 75 districts of Uttar Pradesh state which is received from the Indian Meteorological Department (IMD). Furthermore, analysing the impact of forecasts with different parameters is realized over six major crops Triticum (biological name of wheat), Gram, Barley, Mustard, Sugarcane, and Maize of Uttar Pradesh State. The main objective of the state-of-the-art is efficient crop management and passing the appropriate message to farmers to make suitable decisions as per the weather conditions.

Countries are more concerned about agricultural needs as it is considered to be the essential source of one's life. In our country, agriculture and farming play a vital role in the economy and provide 45% of overall support for economic development. In earlier research, the development of various agricultural support devices was introduced but all were stuck up to a certain level. Remote surveillance, SMS-based agricultural watering systems, and management are a few implementations in the area. But all these implementations are facing some technical challenges due to their complexity and it is hard to maintain the accuracy of these systems. Today’s agricultural demands can be supported by Precision agriculture and Intelligent Crop Farming. This chapter focuses on different aspects of Precision Agriculture and Smart Farming.

Since India is the second-highest populated country in the world and the seventh-largest country in terms of area, which includes hills, plateaus, coastal areas, etc., this situation of land makes a variety of crops and harvest timelines. These timelines seeped into India’s culture and festivals. The harvest planning of farmers became a very challenging task due to the variety of land and multitude of harvest timelines as well. To execute this harvest plan, farmers must survey and map their land, but their limited reach restricts them. In view of these restrictions and limitations, drones can be very helpful for farmers; these drones can improve surveying quality and provide a proper harvest timeline as output. Artificial Intelligence-powered drones will give results in three stages: analysis of field planning, tracking the growth and counting of crops, and finally the ripeness tracking and timing of the harvest.