The potential global distribution of an emerging forest pathogen, Lecanosticta acicola, under a changing climate

Abstract

Brown spot needle blight (BSNB), caused by Lecanosticta acicola (Thüm.) Syd., is an emerging forest disease of Pinus species originating from North America and introduced to Europe and Asia. Severity and spread of the disease has increased in the last two decades in North America and Europe as a response to climate change. No modeling work on spread, severity, climatic suitability, or potential distribution has been done for this important emerging pathogen. This study utilizes a global dataset of 2,970 independent observations of L. acicola presence and absence from the geodatabase, together with Pinus spp. distribution data and 44 independent climatic and environmental variables. The objectives were to (1) identify which bioclimatic and environmental variables are most influential in the distribution of L. acicola; (2) compare four modeling approaches to determine which modeling method best fits the data; (3) examine the realized distribution of the pathogen under climatic conditions in the reference period (1971–2000); and (4) predict the potential future global distribution of the pathogen under various climate change scenarios. These objectives were achieved using a species distribution modeling. Four modeling approaches were tested: regression-based model, individual classification trees, bagging with three different base learners, and random forest. Altogether, eight models were developed. An ensemble of the three best models was used to make predictions for the potential distribution of L. acicola: bagging with random tree, bagging with logistic model trees, and random forest. Performance of the model ensemble was very good, with high precision (0.87) and very high AUC (0.94). The potential distribution of L. acicola was computed for five global climate models (GCM) and three combined pathways of Shared Socioeconomic Pathway (SSP) and Representative Concentration Pathway (SSP-RCP): SSP1-RCP2.6, SSP2-RCP4.5, and SSP5-RCP8.5. The results of the five GCMs were averaged on combined SSP-RCP (median) per 30-year period. Eight of 44 studied factors determined as most important in explaining L. acicola distribution were included in the models: mean diurnal temperature range, mean temperature of wettest quarter, precipitation of warmest quarter, precipitation seasonality, moisture in upper portion of soil column of wettest quarter, surface downwelling longwave radiation of driest quarter, surface downwelling shortwave radiation of warmest quarter and elevation. The actual distribution of L. acicola in the reference period 1971–2000 covered 5.9% of Pinus spp. area globally. However, the model ensemble predicted potential distribution of L. acicola to cover an average of 58.2% of Pinus species global cover in the reference period. Different climate change scenarios (five GCMs, three SSP-RCPs) showed a positive trend in possible range expansion of L. acicola for the period 1971–2100. The average model predictions toward the end of the century showed the potential distribution of L. acicola rising to 62.2, 61.9, 60.3% of Pinus spp. area for SSP1-RCP2.6, SSP2-RCP4.5, SSP5-RCP8.5, respectively. However, the 95% confidence interval encompassed 35.7–82.3% of global Pinus spp. area in the period 1971–2000 and 33.6–85.8% in the period 2071–2100. It was found that SSP-RCPs had a little effect on variability of BSNB potential distribution (60.3–62.2% in the period 2071–2100 for medium prediction). In contrast, GCMs had vast impact on the potential distribution of L. acicola (33.6–85.8% of global pines area). The maps of potential distribution of BSNB will assist forest managers in considering the risk of BSNB. The results will allow practitioners and policymakers to focus surveillance methods and implement appropriate management plans.