The quality of agricultural products relates to the internal structure, which has long been a matter of interest in agricultural scientists. However, inspection methods of the opaque nature of internal information on agricultural products are usually destructive and require sample separation or preparation. X‐ray computed tomography (X‐ray CT) technology is one of the important nondestructive testing (NDT) technologies without sample separation and preparation. In this study, X‐ray CT technology is used to obtain two‐dimensional slice images and three‐dimensional tomographic images of samples. The purpose of the review was to provide an overview of the working principle of X‐ray CT technology, image processing, and analysis. This review aims to focus on the development of the agricultural products (e.g., wheat, maize, rice, apple, beef) and its applications (e.g., internal quality evaluation, microstructure observation, mechanical property measurement, and others) using CT scanner. This paper covers the aspects regarding the advantages and disadvantages of NDT technology, especially the unique advantages and limitations of X‐ray CT technology on the quality inspection of agricultural products. Future prospects of X‐ray CT technology are also put forward to become indispensable to the quality evaluation and product development on agricultural products.

Land use/land cover (LULC) changes are among the most significant human-caused global variations affecting the natural environment and ecosystems. Pakistan’s LULC patterns have undergone huge changes since the 1900s, with no clear mitigation plan. This paper aims to determine LULC and normalized difference vegetation index (NDVI) changes as well as their causes in Pakistan’s Southern Punjab province over four different periods (2000, 2007, 2014, and 2021). Landsat-based images of 30 m × 30 m spatial resolution were used to detect LULC changes, while NDVI dynamics were calculated using Modis Product MOD13Q1 (Tiles: h24 v5, h24 v6) at a resolution of 250 m. The iterative self-organizing (ISO) cluster method (object meta-clustering using the minimal distance center approach) was used to quantify the LULC changes in this research because of its straightforward approach that requires minimal human intervention. The accuracy assessment and the Kappa coefficient were calculated to assess the efficacy of results derived from LULC changes. Our findings revealed considerable changes in settlements, forests, and barren land in Southern Punjab. Compared to 2000, while forest cover had reduced by 31.03%, settlement had increased by 14.52% in 2021. Similarly, forest land had rapidly been converted into barren land. For example, barren land had increased by 12.87% in 2021 compared to 2000. The analysis showed that forests were reduced by 31.03%, while settlements and barren land increased by 14.52% and 12.87%, respectively, over the twenty year period in Southern Punjab. The forest area had decreased to 4.36% by 2021. It shows that 31.03% of forest land had been converted to urban land, barren ground, and farmland. Land that was formerly utilized for vegetation had been converted into urban land due to the expansion of infrastructure and the commercial sector in Southern Punjab. Consequently, proper monitoring of LULC changes is required. Furthermore, relevant agencies, governments, and policymakers must focus on land management development. Finally, the current study provides an overall scenario of how LULC trends are evolving over the study region, which aids in land use planning and management.

For developing countries, scarcity of climatic data is the biggest challenge, and model development with limited meteorological input is of critical importance. In this study, five data intelligent and hybrid metaheuristic machine learning algorithms, namely additive regression (AR), AR-bagging, AR-random subspace (AR-RSS), AR-M5P, and AR-REPTree, were applied to predict monthly mean daily reference evapotranspiration (ET₀). For this purpose, climatic data of two meteorological stations located in the semi-arid region of Pakistan were used from the period 1987 to 2016. The climatic dataset includes maximum and minimum temperature (T_max, T_min), average relative humidity (RH_avg), average wind speed (U_x), and sunshine hours (n). Sensitivity analysis through regression methods was applied to determine effective input climatic parameters for ET₀ modeling. The results of performed regression analysis on all input parameters proved that T_min, RH_Avg, U_x, and n were identified as the most influential input parameters at the studied station. From the results, it was revealed that all the selected models predicted ET₀ at both stations with greater precision. The AR-REPTree model was located furthest and the AR-M5P model was located nearest to the observed point based on the performing indices at both the selected meteorological stations. The study concluded that under the aforementioned methodological framework, the AR-M5P model can yield higher accuracy in predicting ET₀ values, as compared to other selected algorithms.

Accurate and rapid detection of tea shoots within the tea canopy is essential for achieving the automatic picking of famous tea. The current detection models suffer from two main issues: low inference speed and difficulty in deployment on movable platforms, which constrain the development of intelligent tea picking equipment. Furthermore, the detection of tea canopy shoots is currently limited to natural daylight conditions, with no reported studies on detecting tea shoots under artificial light during the nighttime. Developing an all-day tea picking platform would significantly improve the efficiency of tea picking. In view of these problems, the research objective was to propose an all-day lightweight detection model for tea canopy shoots (TS-YOLO) based on YOLOv4. Firstly, image datasets of tea canopy shoots sample were collected under low light (6:30–7:30 and 18:30–19:30), medium light (8:00–9:00 and 17:00–18:00), high light (11:00–15:00), and artificial light at night. Then, the feature extraction network of YOLOv4 and the standard convolution of the entire network were replaced with the lightweight neural network MobilenetV3 and the depth-wise separable convolution. Finally, to compensate for the lack of feature extraction ability in the lightweight neural network, a deformable convolutional layer and coordinate attention modules were added to the network. The results showed that the improved model size was 11.78 M, 18.30% of that of YOLOv4, and the detection speed was improved by 11.68 FPS. The detection accuracy, recall, and AP of tea canopy shoots under different light conditions were 85.35%, 78.42%, and 82.12%, respectively, which were 1.08%, 12.52%, and 8.20% higher than MobileNetV3-YOLOv4, respectively. The developed lightweight model could effectively and rapidly detect tea canopy shoots under all-day light conditions, which provides the potential to develop an all-day intelligent tea picking platform.

In recent years, horticultural plants have frequently suffered significant heat damage due to excessive temperatures. In this study, a horticultural spray cooling system was designed, consisting mainly of a jet fan and spraying system. CFD simulation technology and response surface methodology were used to optimize the design of the jet fan, which improved the thrust of the fan. The length of the inlet section was 300 mm, the length of the outlet section was 300 mm, the length of the cone section was 450 mm, and the diameter of the outlet was 950 mm, where the thrust of the jet fan was 225.06 N. By establishing the CFD model of spray cooling in a tea field and designing a L₉ (3⁴) orthogonal experiment, the effect of the spray parameters on the maximum temperature drop and effective cooling distance was studied, and the best parameters were selected. The simulation results show that the optimum parameters are a spray flow rate of 4.5 kg/s, a droplet diameter of 15–45 μm, a droplet temperature of 298.15 K, and a nozzle double circle layout. Based on the simulation results of the optimized jet fan and spray parameters selected, a spray cooling test bench was established. Field test results show that when the initial ambient temperature was 310.05 K–310.95 K, the maximum temperature drop of the spray cooling fan was 9.1 K, and the cooling distance was approximately 36.0 m. The temperature drop decreased with increasing distance from the fan. This study is of great significance to protect horticultural plants from extremely high temperatures.

Accurate estimation of reference evapotranspiration (ET_o) plays a vital role in irrigation and water resource planning. The Penman–Monteith method recommended by the Food and Agriculture Organization (FAO PM56) is widely used and considered a standard to calculate ET_o. However, FAO PM56 cannot be used with limited meteorological variables, so it is compulsory to choose an alternative model for ET_o estimation, which requires fewer variables. This study built ten machine learning (ML) models based on multi-function, neural network, and tree-based structure against the FAO PM56 method. For this purpose, time series temperature data on a monthly scale are only used to train ML models. The developed ML models were applied to estimate ET_o at different test stations and the obtained results were compared with the FAO PM56 method to verify and validate their performance in ET_o estimation for the selected stations. In addition, multiple statistical indicators, including root-mean-square error (RMSE), coefficient of determination (R²), mean absolute error (MAE), Nash–Sutcliffe efficiency (NSE), and correlation coefficient (r) were calculated to compare the performance of each ML model on ET_o estimation. Among the applied ML models, the ET_o tree boost (TB) ML model outperformed the other ML models in estimating ET_o in diverse climatic conditions based on statistical indicators (R², NSE, r, RMSE, and MAE). Moreover, the observed R², NSE, and r were the highest for the TB ML model, while RMSE and MAE were found to be the lowest at the study sites compared to other applied ML models. Lastly, ET_o point data yielded from the TB ML model was used in an interpolation process to create monthly and annual ET_o maps. Based on the ET_o maps, this study suggests mainly a focus on areas with high ET_o values and proper irrigation scheduling of crops to ensure water sustainability.