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.

Evaluation of tomato production systems at Bowen in mitigating the risk of fruit fly infestation: a systems approach for market access

Queensland fruit flies Bactrocera tryoni and B. neohumeralis are considered major quarantine pests of tomato, a major crop in the horticultural production district around Bowen, North Queensland, Australia. Preharvest and/or postharvest treatments are required to meet the market access requirements of both domestic and international trading partners. The suspension from use of dimethoate and fenthion, the two insecticides used for fruit fly control, has resulted in the loss of both pre and postharvest uses in fresh tomato. Research undertaken quantitatively at Bowen evaluated the effectiveness of pre-harvest production systems without specific fruit fly controls and postharvest mitigation measures in reducing the risk of fruit fly infestation in tomato. A district-wide trapping using cue-lure baited traps was undertaken to determine fruit fly seasonal patterns in relation to the cropping seasons. A total of 17,626 field-harvested and 11,755 pack-house tomatoes were sampled from ten farms over three cropping seasons (2006-2009). The fruit were incubated and examined for fruit fly infestation. No fruit fly infested fruit were recorded over the three seasons in either the field or the pack-house samples. Statistical analyses showed that upper infestation levels were extremely low (between 0.025 and 0.062%) at the 95% confidence level. The trap catches showed a seasonal pattern in fruit fly activity, with low numbers during the autumn and winter months, rising slightly in spring and peaking in summer. This seasonal pattern was similar over the four seasons. The main two species of fruit fly caught were B. tryoni and B. neohumeralis. Based on the results, it is clear that the risk of fruit fly infestation is extremely low under the current production systems in the Bowen region.