Measuring the traction profile on sportsfields: Equipment development and testing

Traction is recognised as an important component of the overall playability and safety of a sportsfield. It relates to the "grip", or footing, provided through an athlete's shoe when in contact with the surface, and is normally measured by the torque generated when a weighted studded disc apparatus is dropped onto the turf and twisted manually. This paper describes the development of an automated traction tester, which mechanises the dropping and twisting of the weighted studded disc. By standardising these operational stages, more repeatable and reliable results can be expected than from the original hand-operated design where positioning of the disc and speed of rotation are controlled manually and so can vary from one measurement to the next. As well as measuring the maximum torque reached during rotation of the studded disc, the automated traction tester generates a profile of torque showing changes over time and calculates the angle through which the studded disc moved before reaching maximum torque. These aspects are now covered by a utility patent (PAT/AU/2004270767). Use of the automated traction tester is illustrated by comparative data for a range of warm-season turfgrasses, by comparisons of traction under different surface conditions generated by wear on Cynodon dactylon cultivars, and by the effects of environment, management and playing patterns on traction across a multi-use sports stadium.

Factors contributing to wear tolerance of Bermudagrass (Cynodon dactylon (L.) Pers., C. dactylon x C. transvaalensis Burtt-Davey) on a sand-based profile under simulated sports field conditions

Wear resistance and recovery of 8 Bermudagrass (Cynodon dactylon (L.) Pers.) and hybrid Bermudagrass (C. Dactylon x C. transvaalensis Burtt-Davey) cultivars grown on a sandbased soil profile near Brisbane, Australia, were assessed in 4 wear trials conducted over a two year period. Wear was applied on a 7-day or a 14-day schedule by a modified Brinkman Traffic Simulator for 6-14 weeks at a time, either during winter-early spring or during summer-early autumn. The more frequent wear under the 7-day treatment was more damaging to the turf than the 14-day wear treatment, particularly during winter when its capacity for recovery from wear was severely restricted. There were substantial differences in wear tolerance among the 8 cultivars investigated, and the wear tolerance rankings of some cultivars changed between years. Wear tolerance was associated with high shoot density, a dense stolon mat strongly rooted to the ground surface, high cell wall strength as indicated by high total cell wall content, and high levels of lignin and neutral detergent fiber. Wear tolerance was also affected by turf age, planting sod quality, and wet weather. Resistance to wear and recovery from wear are both important components of wear tolerance, but the relative importance of their contributions to overall wear tolerance varies seasonally with turf growth rate.

Automating Crop Damage Assessments with Unmanned Aerial Systems and Machine Learning

Agricultural pests are responsible for millions of dollars in crop losses and management costs every year. In order to implement optimal site-specific treatments and reduce control costs, new methods to accurately monitor and assess pest damage need to be investigated. In this paper we explore the combination of unmanned aerial vehicles (UAV), remote sensing and machine learning techniques as a promising methodology to address this challenge. The deployment of UAVs as a sensor platform is a rapidly growing field of study for biosecurity and precision agriculture applications. In this experiment, a data collection campaign is performed over a sorghum crop severely damaged by white grubs (Coleoptera: Scarabaeidae). The larvae of these scarab beetles feed on the roots of plants, which in turn impairs root exploration of the soil profile. In the field, crop health status could be classified according to three levels: bare soil where plants were decimated, transition zones of reduced plant density and healthy canopy areas. In this study, we describe the UAV platform deployed to collect high-resolution RGB imagery as well as the image processing pipeline implemented to create an orthoimage. An unsupervised machine learning approach is formulated in order to create a meaningful partition of the image into each of the crop levels. The aim of this approach is to simplify the image analysis step by minimizing user input requirements and avoiding the manual data labelling necessary in supervised learning approaches. The implemented algorithm is based on the K-means clustering algorithm. In order to control high-frequency components present in the feature space, a neighbourhood-oriented parameter is introduced by applying Gaussian convolution kernels prior to K-means clustering. The results show the algorithm delivers consistent decision boundaries that classify the field into three clusters, one for each crop health level as shown in Figure 1. The methodology presented in this paper represents a venue for further esearch towards automated crop damage assessments and biosecurity surveillance.