查看更多>>摘要：? 2022 Elsevier B.V.Pecans are a specialty crop in New Mexico's Lower Rio Grande Valley (LRGV), a region that produces around 30% of pecans in USA. Pecans are also a major water consumer, requiring 1200–1300 mm depth for maximum yield in this region. The combination of prolonged drought and increasing competition for water among various water consumers has created an urgency for the efficient use of scarce water resources in the LRGV. More efficient water management through the real-time irrigation scheduling is one method to promote reduced water application in agriculture. This study was conducted to calibrate and validate a new modified model for estimating the pecan actual evapotranspiration (ETa) based on canopy temperature using thermal images taken from an Unmanned Aerial Vehicle (UAV) during three growing seasons in a drip irrigated pecan orchard. A capacity to estimate the relation between ETa and canopy temperature provides an important information to guide water management choices. The Simplified Surface Energy Balance (SSEBop) model was modified and used for calibration and validation. Applied irrigation water based on ETa was used to calibrate and validate the proposed modified model. The scaling factor of K in the SSEBop model was calculated as 0.75 through the calibration process. Findings showed a good agreement between estimated pecan ETa using modified SSEBop model and applied water based on ETa during calibration (R2 = 0.72, RMSE = 0.6 mm/d, MAE = 0.48 mm/d) and validation period (R2 = 0.90, RMSE = 0.24 mm/d, MAE = 0.22 mm/d). Also, findings confirmed the utility of modified model for estimating monthly pecan ETa (RMSE = 8.87 mm/month, MAE = 6.55 mm/month). The proposed modified model provides pecan farmers with a simple real-time irrigation scheduling tool where they can better practice precision irrigation. Although the modified model was calibrated and validated for irrigation scheduling in the LRGV, it has potential to see application for other locations with different crops using similar calibration approach.
查看更多>>摘要：? 2022Newcastle disease (ND) is a common disease in poultry that has a great impact on poultry health and production. ND has destructive effects on the respiratory system, such as altering the acoustic features of bird vocalizations. For this reason, this research proposed a new method, the deep poultry vocalization network (DPVN), for the early detection of ND based on poultry vocalization. The method combined multiwindow spectral subtraction and high-pass filtering to reduce the influence of noise. In order to detect poultry vocalizations automatically, a multiple subband poultry vocalization endpoint detection method was proposed in this paper. The performance of the detection method was evaluated using the intersection-over-union (IOU) between the detected vocalizations and ground truth vocalizations. The recall of the detection method was 95.11%, and the precision was 96.54%. The audio features of poultry vocalizations are extracted by sound technology and used as the input of a deep learning network to recognize the vocalizations of poultry with Newcastle disease. Five different models were compared in the experiments. The method used in this paper achieves the best performance and the highest accuracy, recall and F1-score of 98.50%, 96.60% and 97.33%, respectively. The accuracies within the first, second, third and fourth days after infection were 82.15%, 90.00%, 93.60% and 98.50%, respectively. The experimental results show that the method proposed in this paper can be used to detect Newcastle disease in the early stage. It will be significant for improving animal welfare and the automated monitoring of poultry production.
查看更多>>摘要：? 2022 Elsevier B.V.Warehouses that operate under controlled micro-climates are necessary to reduce the deterioration of fresh produce, but they are also costly to operate. Developing an efficient operation regime for these premises while considering energy costs, demand, and harvesting requirements is crucial to managing the food supply chain sustainably and profitably. This paper proposes a method to develop an operation regime by solving a multi-period, multi-product, multi-warehouse inventory control optimization problem that originates from the management of agri-fresh products from an Australian company. We propose a mixed-integer quadratic programming model for this problem. A significant challenge is that each product has a specific deterioration rate over storage, which differs in each warehouse mode. Our model allows for two different operational modes for warehouses, each with different electricity consumption, affecting the time the products remain fresh. The objective function of the model minimizes the total inventory costs. The model provides the optimal inventory flow of each product, the optimal number of active warehouses, the optimal operational length of warehouses, and the optimal mode of warehouses in each period. We solve the model using Gurobi and integrate three other solution approaches based on model properties, which reduce the computational time by half. The model is tested using real data from the case study, an Australian agri-fresh company. The results indicate a reduction in total cost by 8% and quantity of product deterioration by 20%. We also investigate the impacts of variations in demand and supply caused by growing or shrinking markets in our case study under different scenarios and instance sizes of the problem and analyze the impact in solution times that are observed in practice.
NSTL
Elsevier