Smart agriculture has become crucial in meeting the increasing dietary needs of a growing population, particularly in countries where agriculture has significant economic impact. Deep learning techniques, such as convolutional neural networks and recurrent neural networks, have been extensively researched and applied in agriculture in recent years. In this study, recent research articles on deep learning in agriculture over the past five years are analyzed to identify key contributions and challenges. The study has also explored agriculture parameters monitored by the internet of things and used them to train the deep learning algorithms for analysis. The study compares various factors across different studies, including the agriculture area of focus, dataset used, deep learning model and framework, data preprocessing and augmentation methods, and accuracy of results.
TopIntroduction
Deep learning-based agriculture monitoring and forecasting is a field of study that uses deep learning (DL) techniques to analyze and predict agricultural patterns and outcomes. This technology has potential to revolutionize the way we approach farming by providing farmers with real-time data and insights into crop health, yield, and soil moisture levels (Muhammad et al., 2021). The DL algorithms are using large data to identify patterns and make predictions. In agriculture, this can include data such as satellite imagery, weather patterns, soil moisture levels, and crop health metrics. By analyzing these data, deep learning models can provide the insights that can help farmers to make informed decisions about planting, harvesting, and crop management (Garg and Rani, 2020).
The deep learning applications in agriculture includes namely, crop yield prediction, disease detection, and irrigation management, etc. By predicting crop yields, farmers can adjust planting and harvesting schedules to maximize their output. Disease detection can help farmers to identify and treat crop diseases before they become widespread, saving time and resources. And by monitoring soil moisture levels as well as weather patterns, farmers can optimize the irrigation systems to conserve water and increase crop yields (Muhammad et al. 2021). Overall, the deep learning-based agriculture monitoring and forecasting has potential to revolutionize the agriculture industry by providing real-time data and insights that can help them to make decisions with improve crop yields (Sladojevic et al., 2020).
Smart agriculture having several challenges as shown Figure 1. Thus, there is a need of smart agriculture monitoring and forecasting system that can help farmers in following ways:
Increasing food production: The global population is expected to reach 9.7 billion by 2050, so food production needs to increase by 70% to meet the necessity. Agriculture monitoring and forecasting can help farmers optimize their yields and increase production, thereby contributing to food security (Sladojevic et al., 2020) Resource optimization: Agriculture monitoring and forecasting can help farmers optimize use of resources like water, fertilizers, and pesticides. By providing real-time data on soil moisture levels and weather patterns, farmers can adjust their irrigation systems as well as reduce water usage. Similarly, by using predictive analytics to identify potential crop diseases, farmers can reduce the amount of pesticides they use, which can have a positive impact on the environment (Fountas et al., 2020).
Cost reduction: Agriculture monitoring and forecasting can help farmers reduce costs by optimizing their use of resources and improving their crop yields. By using real-time data to make informed decisions, farmers can reduce waste and increase their profits (Muhammad et al., 2021).
Risk mitigation: Agriculture is a high-risk industry, with weather patterns, pests, and diseases all posing a threat to crops. Agriculture monitoring and forecasting can help farmers mitigate these risks by providing early warning systems for weather events and identifying potential crop diseases before they become widespread (Boulent, et al. 2019).
Sustainable agriculture: Agriculture monitoring and forecasting can help farmers adopt sustainable practices by reducing their reliance on chemical inputs and optimizing the use of resources. By adopting sustainable practices, farmers can reduce their environmental impact and ensure the long-term viability of their operations (Fountas et al., 2020; Boulent et al. 2019).