Assessment of ecosystems: A system for rigorous and rapid mapping of floodplain forest condition for Australia's most important river

Abstract

Methods that provide rapid assessments of changing ecosystems at multiple scales are needed to inform management to address undesirable change. We developed a remote-sensing method in partnership with, and for use by, natural resource managers to predict annually stand condition of floodplain forests along Australia's longest river, the Murray River. A measure of stand condition, which was developed in collaboration with responsible natural resource managers, is a function of plant area index, crown extent, and the percentage live basal area. We surveyed a broad range of spatial and temporal variation in condition, built predictive stand-condition models using satellite-derived variables, and validated predictions with surveys of new sites. A multiyear model using data from 2 drought years and a year following extensive floods provided better predictions of stand condition than did models on the basis of the data for individual years.The model provided good predictions for data collected after the build for 50 sites and for resurveys of build sites in later years (R 2 ≥ 0.86). There was limited, temporary improvement in stand condition after the extensive flooding (2010 to late 2010) that followed a 13-year (1997 to early 2010) drought. Forest condition can be mapped accurately and annually at medium resolution (25 × 25 m) for large areas (100,000s ha) if quantitative ground surveys, satellite imagery, machine learning, and future validation are combined. Regular assessments of forest condition can be related to likely causes of change by using regular, rapid assessments and hence can provide important management information.

Assessment of environmental flow scenarios using state‐and‐transition models

“…Nevertheless, anecdotally our results support the observed widespread poor condition of water‐dependent vegetation in the region under a regulated flow regime (i.e. the Development scenario; Cunningham, Griffioen, White, & Mac Nally, ), as well as the limited response to individual flow events by woody vegetation that is in poor condition (e.g. Souter et al., ).…”

“…We did not consider the role of environmental engineering "works and measures," such as the use of regulators and levees to divert water onto floodplains at a lower river stage than required T A B L E 1 Summary of the ecological characteristics for each of the vegetation types included in the modelling. Note river red gum woodland has a lower canopy density (Cunningham et al, 2017) and requires less frequent flooding than river red gum forest ( | 807 naturally, which may provide higher inundation frequencies to some parts of the floodplain than are modelled here (Bond, 2016). Such approaches are not without their risks Pittock, Finlayson, & Howitt, 2012;Stoffels, Clarke, Rehwinkel, Mccarthy, & Tonn, 2014), but are being examined and in some cases implemented at various sites within the southern MDB.…”

Flood Prediction Using Machine Learning Models: Literature Review

“…Reference [200] SVM was demonstrated as a potential candidate for the prediction of long-term discharges, outshining the ANN. In a similar approach, Reference [205] proposed an SVM-based model for estimating soil moisture using remote-sensing data, and the results were Reference [204], employed RT to model forest flood. Data from 2009-2012 at 50 sites were used for model building.…”

Flood Prediction Using Machine Learning, Literature Review

“…The SVM model shown to be more accurate and easier to build comparing to BPNN and MLR. [182], employed the RT to model forest flood. The data from 2009-2012 of 50 sites used for model building.…”