The early and precise identification of the different phenological stages of the bean (Phaseolus vulgaris L.) allows for the determination of critical and timely moments for the implementation of certain agricultural activities that contribute in a significant manner to the output and quality of the harvest, as well as the necessary actions to prevent and control possible damage caused by plagues and diseases. Overall, the standard procedure for phenological identification is conducted by the farmer. This can lead to the possibility of overlooking important findings during the phenological development of the plant, which could result in the appearance of plagues and diseases. In recent years, deep learning (DL) methods have been used to analyze crop behavior and minimize risk in agricultural decision making. One of the most used DL methods in image processing is the convolutional neural network (CNN) due to its high capacity for learning relevant features and recognizing objects in images. In this article, a transfer learning approach and a data augmentation method were applied. A station equipped with RGB cameras was used to gather data from images during the complete phenological cycle of the bean. The information gathered was used to create a set of data to evaluate the performance of each of the four proposed network models: AlexNet, VGG19, SqueezeNet, and GoogleNet. The metrics used were accuracy, precision, sensitivity, specificity, and F1-Score. The results of the best architecture obtained in the validation were those of GoogleNet, which obtained 96.71% accuracy, 96.81% precision, 95.77% sensitivity, 98.73% specificity, and 96.25% F1-Score.

This work aimed to evaluate the ability of lipase extract powder obtained from Leonotis nepetifolia seed for enzyme-catalyzed biodiesel production using Leonotis nepetifolia oil, commercial olive oil, and waste cooking oil as substrates. The lipase extract powder showed an enzymatic activity and hydrolysis percentage of 24.7 U/g and 21.31%, respectively, using commercial olive oil as a reference. Transesterification reaction conditions were 40 g of substrate, 34 °C, molar ratio oil: methanol of 1:3, lipase extract powder 20 wt%, phosphates buffer (pH 4.8) 20 wt%, and a reaction time of 8 h. Transesterification yields of 74.5%, 71.5%, and 69.3% for commercial olive oil, waste cooking oil, and Leonotis nepetifolia oil were obtained, respectively. Biodiesel physicochemical parameters were analyzed and compared with the international standards: EN 14214 (European Union) and ASTM D6751 (American Society for Testing and Materials). The biodiesel’s moisture and volatile matter percentages, iodine index, cooper strip corrosion, and methyl esters content conformed to the standards’ specifications. The fatty acid methyl ester content of the vegetable oils showed the presence of methyl oleate after enzyme-catalyzed transesterification. This study reveals that biodiesel production catalyzed by lipase extract powder from Leonotis nepetifolia could be a viable alternative, showing that transesterification yields competitive results.

The high demand for sustainable biodiesel feedstocks has led to the exploration of innovative strategies to enhance lipid productivity in microalgae. This study introduces a push–pull strategy to optimize lipid accumulation in Nannochloropsis oculata. The benzyl amino purine (BAP) and naphthalene acetic acid (NAA) stimulation, acting as the ‘push’ component, significantly boost growth and nutrient stress tolerance. Meanwhile, the ‘pull’ component, nitrogen (N) deficiency, triggers lipid biosynthesis. A Box–Behnken design was employed to optimize the factors named BAP fraction (0–1), total phytohormone (PH) BAP/NAA mix dose (0–20 ppm), and N-concentration (0–50%). The combined BAP/NAA treatment significantly increased biomass (15% higher than the control) and mitigated N-stress with higher doses (20 ppm). Lipid yield surged from 12.4% to 38.87% under optimized conditions (23.25% N, 39.5 ppm NAA, and BAP fraction 0). The push–pull strategy contributed to boosting lipid synthesis and balancing biomass production. N-limitation and total PH dosage were the determining factors in this strategy. This work demonstrates the potential of the push–pull strategy in increasing lipid accumulation, offering a promising and optimistic solution for biodiesel production at scale from microalgae. By reducing dependence on fossil fuels, N. oculata emerges as a reliable feedstock for oil extraction and biodiesel.

Microalgae oil has great potential to address the growing energy demand and dependence on fossil fuels. However, the multilayered cell walls of microalgae hinder efficient extraction and enhanced lipid recovery. In this study, we develop a novel protocol based on near infrared-assisted extraction (NIRAE) technology to extract efficiently total lipids from Scenedesmus obliquus . Under a greener solvent extraction approach, the effect of nine non-polar/polar solvent systems in various ratios on lipid yield was tested, and the results were compared with Soxhlet, Folch, and Bligh–Dyer methods. The highest oil yields were NIRAE 15.43%, and Soxhlet 22.24%, using AcoEt/MeOH (1:2 v/v). For Folch and Bligh–Dyer, 9.11 and 10%, respectively. The optimized NIRAE conditions obtained using response surface methodology (RSM): 43.8 min, solvent/biomass 129.90:1 (m/v), and AcOEt/MeOH 0.57:2.43 (v/v) increased the oil yield significantly to 24.20%. In contrast to conventional methods, the overall optimized NIRAE process satisfied the requirements of a green extraction because of the simple and safe operation, less solvent toxicity, lower extraction time, and solvent and energy consumption.