Search

Summary: Landscape rehabilitation following mining is required to be resilient to disturbance impacts such as fire, drought and disease. As mining companies undergo the process of rehabilitation certification and mine closure, there are notable knowledge gaps on the ecological risks associated with mature rehabilitated landscapes, based largely on the assumption that rehabilitation is analogous to reference communities. However, the response to fire disturbance across a range of landscapes remains largely untested and in particular there is limited understanding of recovery traits of plant species that occur naturally or are commonly seeded into rehabilitation. In August 2018, a controlled fire was applied to 37 hectares of 12‐year‐old coal‐mine rehabilitation in central Queensland, Australia. We used a combination of (i) ground plot surveys and (ii) drone imagery to compare the vegetation response of burnt woody species to unburnt controls prior to, and for, two years following the fire. The survival of the most dominant shrub species found on the rehabilitation site was significantly impacted by the fire. Old Man Saltbush (Atriplex nummularia Lindl. subsp. nummularia) recorded significant post‐fire mortality, with ground surveys recording an average reduction of 89% of stems per hectare across the burnt site, while unburnt controls remained unchanged. The plot data analysis was supported with high spatial and temporal resolution drone imagery, classified using a Random Forest machine‐learning approach. Change analysis of these maps showed a significant decline of 82% in Old Man Saltbush plant density and 92% reduction in foliage cover following the fire. In addition, the mean canopy area of individual Old Man Saltbush shrubs reduced significantly from a pre‐fire mean of 11.3 to 4.8 m2 two years following the fire. A spatial proximity analysis showed that those individuals that survived the fire were located significantly closer to unburnt areas and bare spoil, indicating that discontinuous ground fuel loads can greatly improve the survivability of individuals. This study provides new evidence on the contested fire sensitivity of Old Man Salt bush and demonstrates the risk that future climate‐driven extreme events may have on the resilience of novel ecosystems. [ABSTRACT FROM AUTHOR]

This study evaluates the ability of machine learning algorithms to classify tropical depressions (TDs) and tropical storms (TSs) in the western region of the southwest Pacific Ocean (SWPO). Decision rules are generated to predict the environment required for a depression to fully develop into a mature storm, and the most influential predictors in the classification decision are ranked. TD and TS are discriminated based on a maximum sustained wind speed threshold (≥17 ms−1). Various aerosol, thermodynamic, and dynamic parameters are extracted closest to the initiation point of each non‐developing and developing sample. The covariates associated with each labelled sample are used to train a decision tree and random forest model. Results using a testing dataset suggest the random forest approach more accurately distinguishes between non‐developing and developing samples. The classification accuracy of the decision tree and random forest are 72% and 91%, respectively. Random forest outperformed the decision tree by providing higher accuracy in test data. The most important variables for binary classification are sea salt aerosol optical depth (AOD), 1,000 mb relative humidity, and sea surface temperature. AOD is a quantitative estimate of the aerosols presents in the air through the extinction of a ray of light as it passes through the atmosphere. Mean composite maps constructed in an unsupervised manner have been created for the most important variables identified by the random forest classifier during TD and TS events to highlight the difference in geophysical and aerosol variables' climatology during the two different classifications. This work will advance the risk management strategies for northeastern Australia and other SWPO basin islands to control their tropical cyclone related losses through prioritizing forecasting variables that are the strongest predictors of the strengthening of tropical depressions into tropical cyclones. [ABSTRACT FROM AUTHOR]

Despite their size and contribution to the global carbon cycle, we have limited understanding of tropical savannas and their current trajectory with climate change and anthropogenic pressures. Here we examined interannual variability and externally forced long‐term changes in carbon and water exchange from a high rainfall savanna site in the seasonal tropics of north Australia. We used an 18‐year flux data time series (2001–2019) to detect trends and drivers of fluxes of carbon and water. Significant positive trends in gross primary productivity (GPP, 15.4 g C m2 year−2), ecosystem respiration (Reco, 8.0 g C m2 year−2), net ecosystem productivity (NEE, 7.4 g C m2 year−2) and ecosystem water use efficiency (WUE, 0.0077 g C kg H2O−1 year−1) were computed. There was a weaker, non‐significant trend in latent energy exchange (LE, 0.34 W m−2 year−1). Rainfall from a nearby site increased statistically over a 45‐year period during the observation period. To examine the dominant drivers of changes in GPP and WUE, we used a random forest approach and a terrestrial biosphere model to conduct an attribution experiment. Radiant energy was the dominant driver of wet season fluxes, whereas soil water content dominated dry season fluxes. The model attribution suggested that [CO2], precipitation and Tair accounting for 90% of the modelled trend in GPP and WUE. Positive trends in fluxes were largest in the dry season implying tree components were a larger contributor than the grassy understorey. Fluxes and environmental drivers were not significant during the wet season, the period when grasses are active. The site is potentially still recovering from a cyclone 45 years ago and regrowth from this event may also be contributing to the observed trends in sequestration, highlighting the need to understand fluxes and their drivers from sub‐diurnal to decadal scales. [ABSTRACT FROM AUTHOR]

Aim: Many species are adapted to a particular fire regime and major deviations from that regime may lead to localized extinction. Here, we quantify immaturity risks to an obligate‐seeder forest tree using an objectively designed climate model ensemble and a probabilistic fire regime simulator to predict future fire regimes. Location: Alpine ash (Eucalyptus delegatensis) distribution, Victoria, south‐eastern Australia. Methods: We used a fire regime model (FROST) with six climate projections from a climate model ensemble across 3.7 million hectares of native forest and non‐native vegetation to examine immaturity risks to obligate‐seeder forests dominated by alpine ash (Eucalyptus delegatensis), which has a primary juvenile period of approximately 20 years. Our models incorporated current and future projected climate including fuel feedbacks to simulate fire regimes over 100 years. We then used Random Forest modelling to evaluate which spatial characteristics of the landscape were associated with high immaturity risks to alpine ash forest patches. Results: Significant shifts to the fire regime were predicted under all six future climate projections. Increases in both wildfire extent (total area burnt, area burnt at high intensity) and frequency were predicted with an average increase of up to 110 hectares burnt annually by short‐interval fires (i.e., within the expected minimum time to reproductive maturity). The immaturity risk posed by short‐interval fires to alpine ash forest patches was well explained by Random Forest models and varied with both location and environmental variables. Main conclusions: Alpine ash forests are predicted to be burned at greater intensities and shorter intervals under future fire regimes. About 67% of the current alpine ash distribution was predicted to be at some level of immaturity risk over the 100‐year modelling period, with the greatest risks to those patches located on the periphery of the current distribution, closer to roads or surrounded by a drier landscape at lower elevations. [ABSTRACT FROM AUTHOR]

Understanding vegetation recovery after drought is critical for projecting vegetation dynamics in future climates. From 1997 to 2009, Australia experienced a long‐lasting drought known as the Millennium Drought (MD), which led to widespread reductions in vegetation productivity. However, vegetation recovery post‐drought and its determinants remain unclear. This study leverages remote sensing products from different sources—fraction of absorbed photosynthetically active radiation (FPAR), based on optical data, and canopy density, derived from microwave data—and random forest algorithms to assess drought recovery over Australian natural vegetation during a 20‐year period centered on the MD. Post‐drought recovery was prevalent across the continent, with 6 out of 10 drought events seeing full recovery within about 6 months. Canopy density was slower to recover than leaf area seen in FPAR. The probability of full recovery was most strongly controlled by drought return interval, post‐drought hydrological condition, and drought length. Full recovery was seldom observed when drought events occurred at intervals of 3 months or less, and moderately dry (standardized water balance anomaly [SWBA] within [−1, −0.76]) post‐drought conditions resulted in less complete recovery than wet (SWBA > 0.3) post‐drought conditions. Press droughts, which are long term but not extreme, delayed recovery more than pulse droughts (short term but extreme) and led to a higher frequency of persistent decline. Following press droughts, the frequency of persistent decline differed little among biome types but peaked in semi‐arid regions across aridity levels. Forests and savanna required the longest recovery times for press drought, while grasslands were the slowest to recover for pulse drought. This study provides quantitative thresholds that could be used to improve the modeling of ecosystem dynamics post‐drought. [ABSTRACT FROM AUTHOR]

Summary: Serrated Tussock (Nassella trichotoma) is a weed that invades native grasslands in southern Australia. It is frequently controlled using extensive and costly chemical control. We describe a tool aimed at grassland reserve managers that provides guidance about the suitability of different chemical control techniques, including knapsack, boom and aerial spraying. The tool takes the attributes of any site and predicts the suitability of each technique. The tool was built using random forests trained on a dataset of practitioner judgements. We discuss the applications and limitations of the tool. [ABSTRACT FROM AUTHOR]

Lightning-caused wildfires are a significant contributor to burned areas, with lightning ignitions remaining one of the most unpredictable aspects of the fire environment. There is a clear connection between fuel moisture and the probability of ignition; however, the mechanisms are poorly understood and predictive methods are underdeveloped. Establishing a lightning-ignition relationship would be useful in developing a model that would complement early warning systems designed for fire control and prevention. A machine learning (ML) approach was used to define a predictive model for wildfire ignition based on lightning forecasts and environmental conditions. Three different binary classifiers were adopted: a decision tree, an AdaBoost and a Random Forest, showing promising results, with both ensemble methods (Random Forest and AdaBoost) exhibiting an out-ofsample accuracy of 78%. Data provided by a Western Australia wildfire database allowed a comprehensive verification on over 145 lightning-ignited wildfires in regions of Australia during 2016. This highlighted that in a minimum of 71% of the cases the ML models correctly predicted the occurrence of an ignition when a fire was actually initiated. The super-learner developed is planned to be used in an operational context to the enhance information connected to fire management. [ABSTRACT FROM AUTHOR]

Objective: This research aimed to (i) assess the effects of time‐varying predictors (day of the week, month, year, holiday, temperature) on daily ED presentations and (ii) compare the accuracy of five methods for forecasting ED presentations, including four statistical methods and a machine learning approach. Methods: Predictors of ED presentations were assessed using generalised additive models (GAMs), generalised linear models, multiple linear regression models, seasonal autoregressive integrated moving average models and random forest. The accuracy of short‐term (14 days), mid‐term (30 days) and long‐term (365 days) forecasts were compared using two measures of forecasting error. Results: The data are the numbers of presentations to public hospital EDs in South‐East Queensland, Australia, from 2009 to 2015. ED presentations are largely affected by year of presentation, and to a lesser extent by month, day of the week and holidays. Maximum daily temperature is also a significant predictor of ED presentations. Of the four statistical models considered, the GAM had the greatest forecasting accuracy, and produced consistent and coherent forecasts, likely due to its flexibility in modelling complex time‐varying effects. The random forest machine learning approach had the lowest forecasting accuracy, likely due to overfitting the data. Conclusions: Calendar and temperature variables, not previously considered in the Australian literature, were found to significantly impact ED presentations. This study also demonstrates the potential of GAMs as a dual explanatory and forecasting method for the modelling, and more accurate prediction, of ED presentations. [ABSTRACT FROM AUTHOR]