Ramesh Raja Segaran

Severity of salinity accurately detected and classified on a paddock scale with high resolution multispectral satellite imagery

Publisher: Wiley

Date: 27-06-2013

DOI: 10.1002/LDR.1134

Drones count wildlife more accurately and precisely than humans

Publisher: Wiley

Date: 13-02-2018

DOI: 10.1111/2041-210X.12974

Deep learning for environmental conservation

Publisher: Elsevier BV

Date: 10-2019

DOI: 10.1016/J.CUB.2019.08.016

Abstract: The last decade has transformed the field of artificial intelligence, with deep learning at the forefront of this development. With its ability to 'self-learn' discriminative patterns directly from data, deep learning is a promising computational approach for automating the classification of visual, spatial and acoustic information in the context of environmental conservation. Here, we first highlight the current and future applications of supervised deep learning in environmental conservation. Next, we describe a number of technical and implementation-related challenges that can potentially impede the real-world adoption of this technology in conservation programmes. Lastly, to mitigate these pitfalls, we discuss priorities for guiding future research and hope that these recommendations will help make this technology more accessible to environmental scientists and conservation practitioners.

Estimating Mangrove Tree Biomass and Carbon Content: A Comparison of Forest Inventory Techniques and Drone Imagery

Publisher: Frontiers Media SA

Date: 22-01-2020

DOI: 10.3389/FMARS.2019.00784

Stormwater quality improvement potential of an urbanised catchment using water sensitive retrofits into public parks

Publisher: Elsevier BV

Date: 2014

DOI: 10.1016/J.UFUG.2014.01.001

Climate change and the economics of biomass energy feedstocks in semi-arid agricultural landscapes: A spatially explicit real options analysis

Publisher: Elsevier BV

Date: 05-2017

DOI: 10.1016/J.JENVMAN.2017.01.049

Abstract: The economics of establishing perennial species as renewable energy feedstocks has been widely investigated as a climate change adapted ersification option for landholders, primarily using net present value (NPV) analysis. NPV does not account for key uncertainties likely to influence relevant landholder decision making. While real options analysis (ROA) is an alternative method that accounts for the uncertainty over future conditions and the large upfront irreversible investment involved in establishing perennials, there have been limited applications of ROA to evaluating land use change decision economics and even fewer applications considering climate change risks. Further, while the influence of spatially varying climate risk on biomass conversion economic has been widely evaluated using NPV methods, effects of spatial variability and climate on land use change have been scarcely assessed with ROA. In this study we applied a simulation-based ROA model to evaluate a landholder's decision to convert land from agriculture to biomass. This spatially explicit model considers price and yield risks under baseline climate and two climate change scenarios over a geographically erse farming region. We found that underlying variability in primary productivity across the study area had a substantial effect on conversion thresholds required to trigger land use change when compared to results from NPV analysis. Areas traditionally thought of as being quite similar in average productive capacity can display large differences in response to the inclusion of production and price risks. The effects of climate change, broadly reduced returns required for land use change to biomass in low and medium rainfall zones and increased them in higher rainfall areas. Additionally, the risks posed by climate change can further exacerbate the tendency for NPV methods to underestimate true conversion thresholds. Our results show that even under severe drying and warming where crop yield variability is more affected than perennial biomass plantings, comparatively little of the study area is economically viable for conversion to biomass under $200/DM t, and it is not until prices exceed $200/DM t that significant areas become profitable for biomass plantings. We conclude that for biomass to become a valuable ersification option the synchronisation of products and services derived from biomass and the development of markets is vital.

Flinders University

Location: Australia

View Organisation

Flinders University

Location: No location found

View Organisation

University Of Adelaide

Location: No location found

View Organisation

University Of Adelaide

Location: Australia

View Organisation

Industrial Transformation Research Hubs - Grant ID: IH130200027

Start Date: 07-2015

End Date: 06-2020

Amount: $4,308,668.00

Funder: Australian Research Council