Applications of deep-learning models in machine visions for crop/weed identification have remarkably upgraded the authenticity of precise weed management. However, compelling data are required to obtain the desired result from this highly data-driven operation. This study aims to curtail the effort needed to prepare very large image datasets by creating artificial images of maize (Zea mays) and four common weeds (i.e., Charlock, Fat Hen, Shepherd’s Purse, and small-flowered Cranesbill) through conditional Generative Adversarial Networks (cGANs). The fidelity of these synthetic images was tested through t-distributed stochastic neighbor embedding (t-SNE) visualization plots of real and artificial images of each class. The reliability of this method as a data augmentation technique was validated through classification results based on the transfer learning of a pre-defined convolutional neural network (CNN) architecture—the AlexNet; the feature extraction method came from the deepest pooling layer of the same network. Machine learning models based on a support vector machine (SVM) and linear discriminant analysis (LDA) were trained using these feature vectors. The F1 scores of the transfer learning model increased from 0.97 to 0.99, when additionally supported by an artificial dataset. Similarly, in the case of the feature extraction technique, the classification F1-scores increased from 0.93 to 0.96 for SVM and from 0.94 to 0.96 for the LDA model. The results show that image augmentation using generative adversarial networks (GANs) can improve the performance of crop/weed classification models with the added advantage of reduced time and manpower. Furthermore, it has demonstrated that generative networks could be a great tool for deep-learning applications in agriculture.

With ever increasing world population, the demands on food safety and security are also expected to substantially increase over the next few decades. As agronomic practices, agricultural mechanization and plant breeding technologies have already been extensively exploited, novel techniques need to be explored and implemented to enhance crop production. To this end, the emerging area of laser-based technologies has shown potential to bring about another revolution in enhancing quantity, quality, and safety of foods. This paper presents an exhaustive review of the use of five non-invasive non-destructive laser-based techniques in agriculture, namely laser biostimulation, light detection and ranging, laser land levelling, laser-induced fluorescence spectroscopy, and Raman spectroscopy. Herein we provide the advantages, status quo and challenges of each of these techniques and conclude with recommendations for future work. A comprehensive review of literature reveals the untapped potential of laser applications in agriculture that has the potential to unleash the next agricultural revolution.

We report on the performance of a continuous-wave $\mathrm{Nd}\text{:}{\mathrm{GdVO}}_4$ laser in-band diode-pumped at 912 nm with high output power and excellent beam quality. The laser produced an output power of 19.8 W at 1063 nm with an optical efficiency of 59.3% and slope efficiency of 62.7%. The laser threshold was $\sim 2.04\mathrm{W}$ of the absorbed pump power, and the laser output beam quality was $\le 1.2$ in the horizontal and vertical directions. The strength of thermal lensing at full output power (33.4 W of absorbed power) was measured to be an average of 8.6 diopters. It is shown that thermal lensing is reduced by a factor of 2 with respect to the $\mathrm{Nd}\text{:}{\mathrm{YVO}}_4$ lasers, thus opening a way for further output-power scaling.

Nondestructive estimation of physicochemical properties, post-harvest physiology, and level of ripeness of fruits is essential to their automated harvesting, sorting, and handling. Recent research efforts have identified machine vision systems as a promising noninvasive nondestructive tool for exploring the relationship between physicochemical and appearance characteristics of fruits at various ripening levels. In this regard, the purpose of the current study is to provide an intelligent algorithm for estimating two physical properties including firmness, and soluble solid content (SSC), three chemical properties viz. starch, acidity, and titratable acidity (TA), as well as detection of the ripening level of apples (cultivar Red Delicious) using video processing and artificial intelligence. To this end, videos of apples in orchards at four levels of ripeness were recorded and 444 color and texture features were extracted from these samples. Five physicochemical properties including firmness, SSC, starch, acidity, and TA were measured. Using the hybrid artificial neural network-difference evolution (ANN-DE), six most effective features (one texture and five color features) were selected to estimate the physicochemical properties of apples. The physicochemical estimation was then further optimized using a hybrid multilayer perceptron artificial neural network-cultural algorithm (ANN-CA). The results showed that the coefficient of determinations (R²) related to the prediction models for the physicochemical properties were in excess of 0.92. Additionally, the ripeness level of apples was estimated based on physicochemical properties using a hybrid multilayer perceptron artificial neural network-harmonic search algorithm (ANN-HS) classifier. The developed machine vision system examined ripeness levels of 1356 apples in natural orchard environments and achieved a correct classification rate (CCR) of 97.86%.

We have demonstrated what we believe is the first report on the three continuous-wave dual-wavelength operation regimes of a diode-pumped Nd:GdVO ₄ laser using a single birefringent filter plate. The dual-wavelength operation was achieved at the 1063 & 1071 nm, 1063 & 1083 nm and 1083 & 1086 nm by changing the rotation angle of the birefringent filter plate. The maximum output powers were 2.52 W, 1.09 W and 0.8 W, respectively. This corresponds to the optical-to-optical efficiency of 18.8%, 26.6% and 19.5%, respectively, using the absorbed pump power data.