Pine Wilt Disease is one of the most destructive pests affecting coniferous forests. After being infected by the harmful Bursaphelenchus xylophilus nematode, most trees die within one year. The complex spreading pattern of the disease and the tedious hard labor process of diagnosis involving field wood sampling followed by laboratory analysis call for alternative methods to detect and manage the infected areas. Remote sensing comes naturally into play owing to the possibility of covering relatively large areas and the ability to discriminate healthy from sick trees based on spectral characteristics. This paper presents the development of machine learning classification algorithms for the detection of Pine Wilt Disease in Pinus pinaster, performed in the framework of the European Commission’s Horizon 2020 project “Operational Forest Monitoring using Copernicus and UAV Hyperspectral Data” (FOCUS) in two provinces of central Portugal. Five flight campaigns have been carried out in two consecutive years in order to capture a multitemporal variation of disease distribution. Classification algorithms based on a Random Forest approach were separately designed for the acquired very-high-resolution multispectral and hyperspectral data, respectively. Both algorithms achieved overall accuracies higher than 0.91 in test data. Furthermore, our study shows that the early detection of decaying trees is feasible, even before symptoms are visible in the field.

Moderate-resolution satellite imagery is essential to detect conifer tree decline on a regional scale and address the threat caused by pinewood nematode (PWN), (Bursaphelenchus xylophilus. This is a quarantine organism responsible for pine wilt disease (PWD), which has caused substantial ecological and economic losses in the maritime pine (Pinus pinaster) forests of Portugal. This study describes the first instance of a pre-operational algorithm applied to Sentinel-2 imagery to detect PWD-compatible decline in maritime pine. The Random Forest model relied on a pre-wilting and an in-season image, calibrated with data from a 24-month long field campaign enhanced with Worldview-3 data and the analysis of biological samples (hyperspectral reflectance, pigment quantification in needles, and PWN identification). Independent validation results attested to the good performance of the model with an overall accuracy of 95%, particularly when decline affects more than 30% of the 100 m2 pixel of Sentinel-2. Spectral angle mapper applied to hyperspectral measurements suggested that PWN infection cannot be separated from other drivers of decline in the visible-near infrared domain. Our algorithm can be employed to detect regional decline trends and inform subsequent aerial and field surveys, to further investigate decline hotspots.

Pine Wilt Disease is one of the forest pests with high destructive potential, due to its random spreading and the fast evolution of the symptoms. The correct identification of infected trees is critical for the containment of the pest in affected areas. This paper exploits the capabilities of Random Forest classification algorithms designed to spot the infected trees based on remote sensing images. We use as input both multi-and hyperspectral imagery with high spatial resolution, acquired via remotely piloted airborne systems in infected Portuguese forests. For both imagery types, the classification schemes achieve accuracies higher than 0.91. We conclude that Random Forest classification is a feasible method to detect the Pine Wilt Disease in spectral images acquired over wild forests, even at early stages of the infestation.

No abstract

In Portugal, the Cova da Beira region is well-known for the production of Prunus spp. and is considered the main peach production area in the country. In the spring of 2021 and 2022, field surveys in peach and nectarine orchards showed symptoms of decline such as cankers, gummosis, dry branches, abortion of flowers, mummified fruits and the partial or total death of some plants. Brown rot is caused by three species of the genus Monilinia, M. fructigena, M. laxa and M. fructicola, the last is an OEPP/EPPO A2 quarantine organism on peach trees. Brown rot disease had previously been described in the Cova da Beira region, however, the recent high mortality and severity of symptoms raised doubts as to the species involved. Symptomatic plant material was collected from thirteen orchards and used for fungal isolation and molecular detection according to the OEPP/EPPO standard. M. fructicola was confirmed morphologically and molecularly in two orchards, and molecularly (duplex real-time PCR) detected in two others. Whole genome sequencing using Oxford Nanopore MinION was also carried out to confirm the identification. Pathogenicity tests were performed on peach, nectarine and sweet cherry fruit according to Koch’s postulates. Based on all the results obtained, we report the first detection of M. fructicola in P. persica in Portugal.