Simon Pearson’s research while affiliated with University of Lincoln and other places

In this work, we have proposed a novel methodology for greenhouse tomato yield prediction, which is based on a hybrid of an explanatory biophysical model—the Tomgro model, and a machine learning model called CNN-RNN. The Tomgro and CNN-RNN models are calibrated/trained for predicting tomato yields while different fusion approaches (linear, Bayesian, neural network, random forest and gradient boosting) are exploited for fusing the prediction result of individual models for obtaining the final prediction results. The experimental results have shown that the model fusion approach achieves more accurate prediction results than the explanatory biophysical model or the machine learning model. Moreover, out of different model fusion approaches, the neural network one produced the most accurate tomato prediction results, with means and standard deviations of root mean square error (RMSE), r2-coefficient, Nash-Sutcliffe efficiency (NSE) and percent bias (PBIAS) being 17.69 ± 3.47 g/m2, 0.9995 ± 0.0002, 0.9989 ± 0.0004 and 0.1791 ± 0.6837, respectively.

A high resolution dataset is one of the prerequisites for tea chrysanthemum detection with deep learning algorithms. This is crucial for further developing a selective chrysanthemum harvesting robot. However, generating high resolution datasets of the tea chrysanthemum with complex unstructured environments is a challenge. In this context, we propose a novel tea chrysanthemum – generative adversarial network (TC-GAN) that attempts to deal with this challenge. First, we designed a non-linear mapping network for untangling the features of the underlying code. Then, a customized regularization method was used to provide fine-grained control over the image details. Finally, a gradient diversion design with multi-scale feature extraction capability was adopted to optimize the training process. The proposed TC-GAN was compared with 12 state-of-the-art generative adversarial networks, showing that an optimal average precision (AP) of 90.09% was achieved with the generated images (512 × 512) on the developed TC-YOLO object detection model under the NVIDIA Tesla P100 GPU environment. Moreover, the detection model was deployed into the embedded NVIDIA Jetson TX2 platform with 0.1 s inference time, and this edge computing device could be further developed into a perception system for selective chrysanthemum picking robots in the future.

The reduced Tomgro model is one of the popular biophysical models, which can reflect the actual growth process and model the yields of tomato-based on environmental parameters in a greenhouse. It is commonly integrated with the greenhouse environmental control system for optimally controlling environmental parameters to maximize the tomato growth/yields under acceptable energy consumption. In this work, we compare three mainstream evolutionary algorithms (genetic algorithm (GA), particle swarm optimization (PSO), and differential evolutionary (DE)) for calibrating the reduced Tomgro model, to model the tomato mature fruit dry matter (DM) weights. Different evolutionary algorithms have been applied to calibrate 14 key parameters of the reduced Tomgro model. And the performance of the calibrated Tomgro models based on different evolutionary algorithms has been evaluated based on three datasets obtained from a real tomato grower, with each dataset containing greenhouse environmental parameters (e.g., carbon dioxide concentration, temperature, photosynthetically active radiation (PAR)) and tomato yield information at a particular greenhouse for one year. Multiple metrics (root mean square errors (RMSEs), relative root mean square errors (r-RSMEs), and mean average errors (MAEs)) between actual DM weights and model-simulated ones for all three datasets, are used to validate the performance of calibrated reduced Tomgro model.

Tea chrysanthemum detection at its flowering stage is one of the key components for selective chrysanthemum harvesting robot development. However, it is a challenge to detect flowering chrysanthemums under unstructured field environments given variations on illumination, occlusion and object scale. In this context, we propose a highly fused and lightweight deep learning architecture based on YOLO for tea chrysanthemum detection (TC-YOLO). First, in the backbone component and neck component, the method uses the Cross-Stage Partially Dense network (CSPDenseNet) and the Cross-Stage Partial ResNeXt network (CSPResNeXt) as the main networks, respectively, and embeds custom feature fusion modules to guide the gradient flow. In the final head component, the method combines the recursive feature pyramid (RFP) multiscale fusion reflow structure and the Atrous Spatial Pyramid Pool (ASPP) module with cavity convolution to achieve the detection task. The resulting model was tested on 300 field images using a data enhancement strategy combining flipping and rotation, showing that under the NVIDIA Tesla P100 GPU environment, if the inference speed is 47.23 FPS for each image (416 × 416), TC-YOLO can achieve the average precision (AP) of 92.49% on our own tea chrysanthemum dataset. Through further validation, it was found that overlap had the least effect on tea chrysanthemum detection, and illumination had the greatest effect on tea chrysanthemum detection. In addition, this method (13.6M) can be deployed on a single mobile GPU, and it could be further developed as a perception system for a selective chrysanthemum harvesting robot in the future.

Tea chrysanthemum detection at its flowering stage is one of the key components for selective chrysanthemum harvesting robot development. However, it is a challenge to detect flowering chrysanthemums under unstructured field environments given the variations on illumination, occlusion and object scale. In this context, we propose a highly fused and lightweight deep learning architecture based on YOLO for tea chrysanthemum detection (TC-YOLO). First, in the backbone component and neck component, the method uses the Cross-Stage Partially Dense Network (CSPDenseNet) as the main network, and embeds custom feature fusion modules to guide the gradient flow. In the final head component, the method combines the recursive feature pyramid (RFP) multiscale fusion reflow structure and the Atrous Spatial Pyramid Pool (ASPP) module with cavity convolution to achieve the detection task. The resulting model was tested on 300 field images, showing that under the NVIDIA Tesla P100 GPU environment, if the inference speed is 47.23 FPS for each image (416 * 416), TC-YOLO can achieve the average precision (AP) of 92.49% on our own tea chrysanthemum dataset. In addition, this method (13.6M) can be deployed on a single mobile GPU, and it could be further developed as a perception system for a selective chrysanthemum harvesting robot in the future.

Currently, greenhouses are widely applied for plant growth, and environmental parameters can also be controlled in the modern greenhouse to guarantee the maximum crop yield. In order to optimally control greenhouses’ environmental parameters, one indispensable requirement is to accurately predict crop yields based on given environmental parameter settings. In addition, crop yield forecasting in greenhouses plays an important role in greenhouse farming planning and management, which allows cultivators and farmers to utilize the yield prediction results to make knowledgeable management and financial decisions. It is thus important to accurately predict the crop yield in a greenhouse considering the benefits that can be brought by accurate greenhouse crop yield prediction. In this work, we have developed a new greenhouse crop yield prediction technique, by combining two state-of-the-arts networks for temporal sequence processing—temporal convolutional network (TCN) and recurrent neural network (RNN). Comprehensive evaluations of the proposed algorithm have been made on multiple datasets obtained from multiple real greenhouse sites for tomato growing. Based on a statistical analysis of the root mean square errors (RMSEs) between the predicted and actual crop yields, it is shown that the proposed approach achieves more accurate yield prediction performance than both traditional machine learning methods and other classical deep neural networks. Moreover, the experimental study also shows that the historical yield information is the most important factor for accurately predicting future crop yields.

This study aimed to propose an approach for orchard trees segmentation using aerial images based on a deep learning convolutional neural network variant, namely the U-net network. The purpose was the automated detection and localization of the canopy of orchard trees under various conditions (i.e., different seasons, different tree ages, different levels of weed coverage). The implemented dataset was composed of images from three different walnut orchards. The achieved variability of the dataset resulted in obtaining images that fell under seven different use cases. The best-trained model achieved 91%, 90%, and 87% accuracy for training, validation, and testing, respectively. The trained model was also tested on never-before-seen orthomosaic images or orchards based on two methods (oversampling and undersampling) in order to tackle issues with out-of-the-field boundary transparent pixels from the image. Even though the training dataset did not contain orthomosaic images, it achieved performance levels that reached up to 99%, demonstrating the robustness of the proposed approach.

Solar Insecticidal Lamps (SILs) play a vital role in green prevention and control of pests. By embedding SILs in Wireless Sensor Networks (WSNs), we establish a novel agricultural Internet of Things (IoT), referred to as the SIL-IoTs. In practice, the deployment of SIL nodes is determined by the geographical characteristics of an actual farmland, the constraints on the locations of SIL nodes, and the radio-wave propagation in complex agricultural environment. In this paper, we mainly focus on the constrained SIL Deployment Problem (cSILDP) in a mixed-crop farmland, where the locations used to deploy SIL nodes are a limited set of candidates located on the ridges. We formulate the cSILDP in this scenario as a Connected Set Cover (CSC) problem, and propose a Hole Aware Node Deployment Method (HANDM) based on the greedy algorithm to solve the constrained optimization problem. The HANDM is a two-phase method. In the first phase, a novel deployment strategy is utilised to guarantee only a single coverage hole in each iteration, based on which a set of suboptimal locations is found for the deployment of SIL nodes. In the second phase, according to the operations of deletion and fusion, the optimal locations are obtained to meet the requirements on complete coverage and connectivity. Experimental results show that our proposed method achieves better performance than the peer algorithms, specifically in terms of deployment cost.