Controlled environment agriculture (CEA) is an unconventional production system that is resource efficient, uses less space, and produces higher yields. Deep learning (DL) has recently been introduced in CEA for different applications including crop monitoring, detecting biotic and abiotic stresses, irrigation, microclimate prediction, energy efficient controls, and crop growth prediction. However, no review study assess DL’s state of the art to solve diverse problems in CEA. To fill this gap, we systematically reviewed DL methods applied to CEA. The review framework was established by following a series of inclusion and exclusion criteria. After extensive screening, we reviewed a total of 72 studies to extract the useful information. The key contributions of this article are the following: an overview of DL applications in different CEA facilities, including greenhouse, plant factory, and vertical farm, is presented. We found that majority of the studies are focused on DL applications in greenhouses (82%), with the primary application as yield estimation (31%) and growth monitoring (21%). We also analyzed commonly used DL models, evaluation parameters, and optimizers in CEA production. From the analysis, we found that convolutional neural network (CNN) is the most widely used DL model (79%), Adaptive Moment Estimation (Adam) is the widely used optimizer (53%), and accuracy is the widely used evaluation parameter (21%). Interestingly, all studies focused on DL for the microclimate of CEA used RMSE as a model evaluation parameter. In the end, we also discussed the current challenges and future research directions in this domain.

Rapid population growth, rising food demand, and climate change have created significant challenges to meet the water demands for agriculture. Effective irrigation water management is essential to address the world’s water crisis. The transition from conventional, frequently ineffective gravity-driven irrigations to contemporary, pressure-driven precision irrigation methods are explored in this article, addressing the difficulties associated with water-intensive irrigation, the possibility of updating conventional techniques, and the developments in smart and precision irrigation technologies. This study comprehensively analyses published literature of 150 articles from the year 2005 to 2024, based on titles, abstract, and conclusions that contain keywords such as precision irrigation scheduling, water-saving technologies, and smart irrigation systems, in addition to providing potential solutions to achieve sustainable development goals and smart agricultural production systems. Moreover, it explores the fundamentals and processes of smart irrigation, such as open- and closed-loop control, precision monitoring and control systems, and smart monitoring methods based on soil data, plant water status, weather data, remote sensing, and participatory irrigation management. Likewise, to emphasize the potential of these technologies for a more sustainable agricultural future, several smart techniques, including IoT, wireless sensor networks, deep learning, and fuzzy logic, and their effects on crop performance and water conservation across various crops are discussed. The review concludes by summarizing the limitations and challenges of implementing precision irrigation systems and AI in agriculture along with highlighting the relationship of adopting precision irrigation and ultimately achieving various sustainable development goals (SDGs).

The foundation of effectively predicting plant disease in the early stage using deep learning algorithms is ideal for addressing food insecurity, inevitably drawing researchers and agricultural specialists to contribute to its effectiveness. The input preprocessor, abnormalities of the data (i.e., incomplete and nonexistent features, class imbalance), classifier, and decision explanation are typical components of a plant disease detection pipeline based on deep learning that accepts an image as input and outputs a diagnosis. Data sets related to plant diseases frequently display a magnitude imbalance due to the scarcity of disease outbreaks in real field conditions. This study examines the effects of several preprocessing methods and class imbalance approaches and deep learning classifiers steps in the pipeline for detecting plant diseases on our data set. We notably want to evaluate if additional preprocessing and effective handling of data inconsistencies in the plant disease pipeline may considerably assist deep learning classifiers. The evaluation’s findings indicate that contrast limited adaptive histogram equalization (CLAHE) combined with image sharpening and generative adversarial networks (GANs)-based approach for resampling performed the best among the preprocessing and resampling techniques, with an average classification accuracy of 97.69% and an average F1-score of 97.62% when fed through a ResNet-50 as the deep learning classifier. Lastly, this study provides a general workflow of a disease detection system that allows each component to be individually focused on depending on necessity.

Agriculture of Pakistan relies on the Indus basin, which is facing severe water scarcity conditions. Poor irrigation practices and lack of policy reforms are major threats for water and food security of the country. In this research, alternative water-saving strategies are evaluated through a high spatio-temporal water footprint (WF) assessment (1997–2016) for the Punjab and Sindh provinces, which cover an irrigated area of 17 million hectares in the Indus basin of Pakistan. The SPARE:WATER model is used as a spatial decision support tool to calculate the WF and establish alternative management plans for more sustainable water use. The average water consumption (WF_area) is estimated to 182 km³ yr⁻¹, composed of 75% blue water (irrigation water from surface water and groundwater sources), 17% green water (precipitation) and 8% grey water (water used to remove soil salinity or dilute saline irrigation water). Sugarcane, cotton, and rice are highly water-intensive crops, which consume 57% of the annual water use. However, WF_area can be reduced by up to 35% through optimized cropping patterns of the existing crops with the current irrigation settings and even by up to 50% through the combined implementation of optimal cropping patterns and improved irrigation technologies, i.e., sprinkler and drip irrigation. We recommend that the economic impact of these water-saving strategies should be investigated in future studies to inform stakeholders and policymakers to achieve a more sustainable water policy for Pakistan.

Reducing risk from pesticide applications has been gaining serious attention in the last few decades due to the significant damage to human health, environment, and ecosystems. Pesticide applications are an essential part of current agriculture, enhancing cultivated crop productivity and quality and preventing losses of up to 45% of the world food supply. However, inappropriate and excessive use of pesticides is a major rising concern. Precision spraying addresses these concerns by precisely and efficiently applying pesticides to the target area and substantially reducing pesticide usage while maintaining efficacy at preventing crop losses. This review provides a systematic summary of current technologies used for precision spraying in tree fruits and highlights their potential, briefly discusses factors affecting spraying parameters, and concludes with possible solutions to reduce excessive agrochemical uses. We conclude there is a critical need for appropriate sensing techniques that can accurately detect the target. In addition, air jet velocity, travel speed, wind speed and direction, droplet size, and canopy characteristics need to be considered for successful droplet deposition by the spraying system. Assessment of terrain is important when field elevation has significant variability. Control of airflow during spraying is another important parameter that needs to be considered. Incorporation of these variables in precision spraying systems will optimize spray decisions and help reduce excessive agrochemical applications.