Workload Assessment of Tractor Operations with Ergonomic Transducers and Machine Learning Techniques.

Dynamic muscular workload assessments of tractor operators are rarely studied or documented, which is critical to improving their performance efficiency and safety. A study was conducted to assess and model dynamic load on muscles, physiological variations, and discomfort of the tractor operators arriving from the repeated clutch and brake operations using wearable non-invasive ergonomic transducers and data-run techniques. Nineteen licensed tractor operators operated three different tractor types of varying power ranges at three operating speeds (4-5 km/h), and on two common operating surfaces (tarmacadam and farm roads). During these operations, ergonomic transducers were utilized to capture the load on foot muscles (gastrocnemius right [GR] and soleus right [SR] for brake operation and gastrocnemius left [GL], and soleus left [SL] for clutch operation) using electromyography (EMG). Forces exerted by the feet during brake and clutch operations were measured using a custom-developed foot transducer. During the process, heart rate (HR) and oxygen consumption rates (OCR) were also measured using HR monitor and K4b2 systems, and energy expenditure rate (EER) was determined using empirical equation. Post-tractor operation cycle, an overall discomfort rating (ODR) for that operation was manually recorded on a 10-point psychophysical scale. EMG-based maximum volumetric contraction (%MVC) measurements revealed higher strain on GR (%MVC = 43%), GL (%MVC = 38%), and SR (%MVC = 41%) muscles which in normal conditions should be below 30%. The clutch and brake actuation forces were recorded in the ranges of 90-312 N and 105-332 N, respectively and were significantly affected by the operating speed, tractor type, and operating surface (p < 0.05). EERs of the operators were measured in the moderate-heavy to heavy ranges (9-24 kJ/min) during the course of trials, suggesting the need to refine existing clutch and brake system designs. Average operator ODR responses indicated 7.8% operations in light, 48.5% in light-moderate, 25.2% in moderate, 10.7% in moderate-high, and 4.9% operations in high discomfort categories. When evaluated for the possibility of minimizing the number of transducers for physical workload assessment, EER showed moderate-high correlations with the EMG signals (rGR = 0.78, rGL = 0.75, rSR = 0.68, rSL = 0.66). Similarly, actuation forces had higher correlations with EMG signals for all the selected muscles (r = 0.70-0.87), suggesting the use of simpler transducers for effective operator workload assessment. As a means to minimize subjectivity in ODR responses, machine learning algorithms, including K-nearest neighbor (KNN), random forest classifier (RFC), and support vector machine (SVM), predicted the ODR using body mass index (BMI), HR, EER, and EMG at high accuracies of 87-97%, with RFC being the most accurate. Such high-throughput and data-run ergonomic evaluations can be instrumental in reconsidering workplace designs and better fits for end-users in terms of agricultural tractors and machinery systems.

Water Stress Identification of Winter Wheat Crop with State-of-the-Art AI Techniques and High-Resolution Thermal-RGB Imagery.

Timely crop water stress detection can help precision irrigation management and minimize yield loss. A two-year study was conducted on non-invasive winter wheat water stress monitoring using state-of-the-art computer vision and thermal-RGB imagery inputs. Field treatment plots were irrigated using two irrigation systems (flood and sprinkler) at four rates (100, 75, 50, and 25% of crop evapotranspiration [ETc]). A total of 3200 images under different treatments were captured at critical growth stages, that is, 20, 35, 70, 95, and 108 days after sowing using a custom-developed thermal-RGB imaging system. Crop and soil response measurements of canopy temperature (Tc), relative water content (RWC), soil moisture content (SMC), and relative humidity (RH) were significantly affected by the irrigation treatments showing the lowest Tc (22.5 ± 2 °C), and highest RWC (90%) and SMC (25.7 ± 2.2%) for 100% ETc, and highest Tc (28 ± 3 °C), and lowest RWC (74%) and SMC (20.5 ± 3.1%) for 25% ETc. The RGB and thermal imagery were then used as inputs to feature-extraction-based deep learning models (AlexNet, GoogLeNet, Inception V3, MobileNet V2, ResNet50) while, RWC, SMC, Tc, and RH were the inputs to function-approximation models (Artificial Neural Network (ANN), Kernel Nearest Neighbor (KNN), Logistic Regression (LR), Support Vector Machine (SVM) and Long Short-Term Memory (DL-LSTM)) to classify stressed/non-stressed crops. Among the feature extraction-based models, ResNet50 outperformed other models showing a discriminant accuracy of 96.9% with RGB and 98.4% with thermal imagery inputs. Overall, classification accuracy was higher for thermal imagery compared to RGB imagery inputs. The DL-LSTM had the highest discriminant accuracy of 96.7% and less error among the function approximation-based models for classifying stress/non-stress. The study suggests that computer vision coupled with thermal-RGB imagery can be instrumental in high-throughput mitigation and management of crop water stress.

Soil and Climate Geographic Information System Data-Derived Risk Mapping for Grape Phylloxera in Washington State.

Grape phylloxera (Daktulosphaira vitifoliae, syn. Viteus vitifoliae), a destructive root and foliar pest of grapevines, occurs in almost all viticulture regions worldwide. However, certain regions have remained "phylloxera free." Until recently, this included Washington state (United States), where this insect is regulated as a quarantine pest by Washington State Department of Agriculture. In 2019, established phylloxera populations were discovered in Washington. Phylloxera is typically managed by using resistant or tolerant rootstocks. In Washington, most wine grapes are grown on their own roots of the susceptible species Vitis vinifera instead of grafted rootstock, and thus, are at high risk of vine death should they become infested with phylloxera. This article reports development of a phylloxera risk map for Washington state using geographical soil texture (sand content) and soil temperature data. Weighted averages of soil texture data (mapping year: 2016, depth: 0-100 cm) were obtained from United States Department of Agriculture-Natural Resource Conservation Service (USDA-NRCS) and soilgrids. Soil temperature data were obtained from over 200 weather stations of Washington State University's AgWeatherNet network. Threshold-based classifications were performed in Quantum GIS software on the rasterized soil sand content and temperature independently to derive low, moderate, and high-risk areas, with risk defined as site suitability for optimal phylloxera development. The validation identified 22 out of 23 confirmed phylloxera-positive sites as "high risk," and one site as "moderate risk" when considering soil sand content alone. Soil temperature data alone classified 10 sites as "high risk" and 13 sites as "low risk." When soil sand content was combined with soil temperature (as a risk modifier), 10 sites were classified as "high risk," 12 sites as "high-moderate risk" and one site as "moderate-low" risk. Ground-truth comparisons of confirmed positive sites for phylloxera agreed with past research suggesting that soil sand content is the dominant factor influencing phylloxera infestation. Pertinent risk assessment can be an important component for vineyard decision-making, including whether to use rootstocks in vineyard development or replant scenarios. It may also help to focus the initial scouting and identification efforts to sites and may be helpful when tracking and developing solutions for quarantine pests, such as phylloxera.