Deep learning has already been successfully used in the development of decision support systems in various domains. Therefore, there is an incentive to apply it in other important domains such as agriculture. Fertilizers, electricity, chemicals, human labor, and water are the components of total energy consumption in agriculture. Yield estimates are critical for food security, crop management, irrigation scheduling, and estimating labor requirements for harvesting and storage. Therefore, estimating product yield can reduce energy consumption. Two deep learning models, Long Short-Term Memory and Gated Recurrent Units, have been developed for the analysis of time-series data such as agricultural datasets. In this paper, the capabilities of these models and their extensions, called Bidirectional Long Short-Term Memory and Bidirectional Gated Recurrent Units, to predict end-of-season yields are investigated. The models use historical data, including climate data, irrigation scheduling, and soil water content, to estimate end-of-season yield. The application of this technique was tested for tomato and potato yields at a site in Portugal. The Bidirectional Long Short-Term memory outperformed the Gated Recurrent Units network, the Long Short-Term Memory, and the Bidirectional Gated Recurrent Units network on the validation dataset. The model was able to capture the nonlinear relationship between irrigation amount, climate data, and soil water content and predict yield with an MSE of 0.017 to 0.039. The performance of the Bidirectional Long Short-Term Memory in the test was compared with the most commonly used deep learning method, the Convolutional Neural Network, and machine learning methods including a Multi-Layer Perceptrons model and Random Forest Regression. The Bidirectional Long Short-Term Memory outperformed the other models with an $R^2$ score between 0.97 and 0.99. The results show that analyzing agricultural data with the Long Short-Term Memory model improves the performance of the model in terms of accuracy. The Convolutional Neural Network model achieved the second-best performance. Therefore, the deep learning model has a remarkable ability to predict the yield at the end of the season.

Deep Learning has been successfully applied to image recognition, speech recognition, and natural language processing in recent years. Therefore, there has been an incentive to apply it in other fields as well. The field of agriculture is one of the most important fields in which the application of deep learning still needs to be explored, as it has a direct impact on human well-being. In particular, there is a need to explore how deep learning models can be used as a tool for optimal planting, land use, yield improvement, production/disease/pest control, and other activities. The vast amount of data received from sensors in smart farms makes it possible to use deep learning as a model for decision-making in this field. In agriculture, no two environments are exactly alike, which makes testing, validating, and successfully implementing such technologies much more complex than in most other industries. This paper reviews some recent scientific developments in the field of deep learning that have been applied to agriculture, and highlights some challenges and potential solutions using deep learning algorithms in agriculture. The results in this paper indicate that by employing new methods from deep learning, higher performance in terms of accuracy and lower inference time can be achieved, and the models can be made useful in real-world applications. Finally, some opportunities for future research in this area are suggested.

The rapid growth of the world’s population has put significant pressure on agriculture to meet the increasing demand for food. In this context, agriculture faces multiple challenges, one of which is weed management. While herbicides have traditionally been used to control weed growth, their excessive and random use can lead to environmental pollution and herbicide resistance. To address these challenges, in the agricultural industry, deep learning models have become a possible tool for decision-making by using massive amounts of information collected from smart farm sensors. However, agriculture’s varied environments pose a challenge to testing and adopting new technology effectively. This study reviews recent advances in deep learning models and methods for detecting and classifying weeds to improve the sustainability of agricultural crops. The study compares performance metrics such as recall, accuracy, F1-Score, and precision, and highlights the adoption of novel techniques, such as attention mechanisms, single-stage detection models, and new lightweight models, which can enhance the model’s performance. The use of deep learning methods in weed detection and classification has shown great potential in improving crop yields and reducing adverse environmental impacts of agriculture. The reduction in herbicide use can prevent pollution of water, food, land, and the ecosystem and avoid the resistance of weeds to chemicals. This can help mitigate and adapt to climate change by minimizing agriculture’s environmental impact and improving the sustainability of the agricultural sector. In addition to discussing recent advances, this study also highlights the challenges faced in adopting new technology in agriculture and proposes novel techniques to enhance the performance of deep learning models. The study provides valuable insights into the latest advances and challenges in process systems engineering and technology for agricultural activities.

Portable devices play an essential role where edge computing is necessary and mobility is required (e.g., robots in agriculture within remote-sensing applications). With the increasing applications of deep neural networks (DNNs) and accelerators for edge devices, several methods and applications have been proposed for simultaneous crop and weed detection. Although preliminary studies have investigated the performance of inference time for semantic segmentation of crops and weeds in edge devices, performance degradation has not been evaluated in detail when the required optimization is applied to the model for operation in such edge devices. This paper investigates the relationship between model tuning hyperparameters to improve inference time and its effect on segmentation performance. The study was conducted using semantic segmentation model DeeplabV3 with a MobileNet backbone. Different datasets (Cityscapes, PASCAL and ADE20K) were analyzed for a transfer learning strategy. The results show that, when using a model hyperparameter depth multiplier (DM) of 0.5 and the TensorRT framework, segmentation performance mean intersection over union (mIOU) decreased by 14.7% compared to that of a DM of 1.0 and no TensorRT. However, inference time accelerated dramatically by a factor of 14.8. At an image resolution of $1296\times 966$, segmentation performance of 64% mIOU and inference of 5.9 frames per second (FPS) was achieved in Jetson Nano’s device. With an input image resolution of $513\times 513$, and hyperparameters output stride OS = 32 and DM = 0.5, an inference time of 0.04 s was achieved resulting in 25 FPS. The results presented in this paper provide a deeper insight into how the performance of the semantic segmentation model of crops and weeds degrades when optimization is applied to adapt the model to run on edge devices. Lastly, an application is described for the semantic segmentation of weeds embedded in the edge device (Jetson Nano) and integrated with the robotic orchard. The results show good spraying accuracy and feasibility of the method.

In recent years, deep learning algorithms have been successfully applied in the development of decision support systems in various aspects of agriculture, such as yield estimation, crop diseases, weed detection, etc. Agriculture is the largest consumer of freshwater. Due to challenges such as lack of natural resources and climate change, an efficient decision support system for irrigation is crucial. Evapotranspiration and soil water content are the most critical factors in irrigation scheduling. In this paper, the ability of Long Short-Term Memory (LSTM) and Bidirectional LSTM (BLSTM) to model daily reference evapotranspiration and soil water content is investigated. The application of these techniques to predict these parameters was tested for three sites in Portugal. A single-layer BLSTM with 512 nodes was selected. Bayesian optimization was used to determine the hyperparameters, such as learning rate, decay, batch size, and dropout size.The model achieved the values of mean square error values within the range of 0.014 to 0.056 and $R^2$ ranging from 0.96 to 0.98. A Convolutional Neural Network (CNN) model was added to the LSTM to investigate potential performance improvement. Performance dropped in all datasets due to the complexity of the model. The performance of the models was also compared with CNN, traditional machine learning algorithms Support Vector Regression, and Random Forest. LSTM achieved the best performance. Finally, the impact of the loss function on the performance of the proposed models was investigated. The model with the mean square error as loss function performed better than the model with other loss functions.

Precision irrigation and optimization of water use have become essential factors in agriculture because water is critical for crop growth. The proper management of an irrigation system should enable the farmer to use water efficiently to increase productivity, reduce production costs, and maximize the return on investment. Efficient water application techniques are essential prerequisites for sustainable agricultural development based on the conservation of water resources and preservation of the environment. In a previous work, an off-policy deep reinforcement learning model, Deep Q-Network, was implemented to optimize irrigation. The performance of the model was tested for tomato crop at a site in Portugal. In this paper, an on-policy model, Advantage Actor–Critic, is implemented to compare irrigation scheduling with Deep Q-Network for the same tomato crop. The results show that the on-policy model Advantage Actor–Critic reduced water consumption by 20% compared to Deep Q-Network with a slight change in the net reward. These models can be developed to be applied to other cultures with high production in Portugal, such as fruit, cereals, and wine, which also have large water requirements.