The dataset consists of results from two stream mesocosm experiments that were conducted in the summer-autumn of 1996 and 1997 to distinguish the influence of fine sediment loads and nutrient concentrations on benthic macro-invertebrate and algal communities. 11 biological variables were extracted from the results of this experiment and were standardized for the purpose of training neural networks that could be used to diagnose nutrient and fine sediment impacts in field surveys. The 11 variables were selected according to how well they correlated with the experimental treatment levels (high and low values of both nutrients and fine sediments). The 11 variables were: chlorophyll a (mg/m2), macro-invertebrate familial richness, total abundance, and the abundance of <em>Oligochaeta, Leptoperla varia (Gripopterygidae), Nousia spp. (Leptophlebiidae), Austrophlebioides spp. (Leptophlebiidae), Orthocladiinae, Tanypodinae, Tipulidae</em> and larval <em>Scirtidae</em>. These taxa were abundant within and among the stream mesocosm communities and are common in a wide range of Tasmanian rivers. Values for each of 11 biological response variables were standardized by dividing by their average value observed in the experimental controls mesocosm samples from that year. See Magierowski RH, Read SM, Carter SJB, Warfe DM, Cook LS, Lefroy EC, et al. (2015) <i>Inferring Landscape-Scale Land-Use Impacts on Rivers Using Data from Mesocosm Experiments and Artificial Neural Networks.</i> PLoS ONE 10(3): e0120901. https://doi.org/10.1371/journal.pone.0120901 https://doi.org/10.1371/journal.pone.0120901. This data was collected for the purpose of training artificial neural networks that could diagnose nutrient and sediment impacts in Tasmanian rivers. Each of the 11 variables were standardized by their average value observed in the experimental control samples from that year and some experimental treatment effects (Light) were ignored to simplify the neural network training process. Therefore, these data should not be used to make conclusions about the impacts of fine sediments and nutrients in Tasmanian rivers.

There are presence absence records for vegetation and matched hydrological data from 687 1 x 1 m quadrats recorded from 11 wetlands and wetland complexes (28 sampled hydrological gradients (referred to as transects) across the upper and lower southeast of South Australia. Plant data were collected in spring 2013. Hydrological monitoring data at each site consisted of continuous (6 hourly) surface water level data from a state agency monitoring network. Observed water levels at the monitoring instrument on the day of monitoring were related to the observed depth of water at each quadrat, assuming a flat, level water surface and obtain a datum for each quadrat relative to the monitoring instrument. The continuous monitoring record was then used to calculate a range of different hydrological predictors indicating the variation at each quadrat. The hydrological dataset provided are the univariate summary statistics recording different aspects of surface water dynamics for each quadrat. Hydrological predictors (sum-exceedance value, hydroperiod and maximum inundation depth) were calculated for annual and seasonal periods in the three-years prior to plant data collection. See metadata and relevant publication for additional details on calculation. Hydrological predictors for each quadrat are provided in a single matrix of sites by predictors, with relevant location details for the quadrat (xy coordinates, site, transect). Included is a single electrical conductivity class for each transect (ordinal variable - low moderate, high - see metadata). Vegetation data are provided as a single matrix (quadrats x plant functional group) showing presence absence of each functional group in each quadrat. There is also a lookup table giving the assignment of each plant species to a plant functional group.