scholarly journals Temporal Hydrological Drought Index Forecasting for New South Wales, Australia Using Machine Learning Approaches

Atmosphere ◽  
2020 ◽  
Vol 11 (6) ◽  
pp. 585 ◽  
Author(s):  
Abhirup Dikshit ◽  
Biswajeet Pradhan ◽  
Abdullah M. Alamri
Keyword(s):  
Drought Index ◽  
New South ◽  
New South Wales ◽  
Temporal Trends ◽  
Mitigation Strategies ◽  
Sea Surface ◽  
Dominant Factor ◽  
Economic Losses ◽  
Support Vector ◽  
South Wales

Droughts can cause significant damage to agriculture and water resources leading to severe economic losses. One of the most important aspects of drought management is to develop useful tools to forecast drought events, which could be helpful in mitigation strategies. The recent global trends in drought events reveal that climate change would be a dominant factor in influencing such events. The present study aims to understand this effect for the New South Wales (NSW) region of Australia, which has suffered from several droughts in recent decades. The understanding of the drought is usually carried out using a drought index, therefore the Standard Precipitation Evaporation Index (SPEI) was chosen as it uses both rainfall and temperature parameters in its calculation and has proven to better reflect drought. The drought index was calculated at various time scales (1, 3, 6, and 12 months) using a Climate Research Unit (CRU) dataset. The study focused on predicting the temporal aspect of the drought index using 13 different variables, of which eight were climatic drivers and sea surface temperature indices, and the remainder were various meteorological variables. The models used for forecasting were an artificial neural network (ANN) and support vector regression (SVR). The model was trained from 1901–2010 and tested for nine years (2011–2018), using three different performance metric scores (coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). The results indicate that ANN was better than SVR in predicting temporal drought trends, with the highest R2 value of 0.86 for the former compared to 0.75 for the latter. The study also reveals that sea surface temperatures and the climatic index (Pacific Decadal Oscillation) do not have a significant effect on the temporal drought aspect. The present work can be considered as a first step, wherein we only study the temporal trends, towards the use of climatological variables and drought incidences for the NSW region.

Contrasting temporal trends in lung cancer incidence by socioeconomic status among women in New South Wales, Australia, 1985–2009

Lung Cancer ◽  
2017 ◽  
Vol 108 ◽  
pp. 55-61 ◽  
Author(s):  
Xue Qin Yu ◽  
Qingwei Luo ◽  
Clare Kahn ◽  
Paul Grogan ◽  
Dianne L. O’Connell ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Socioeconomic Status ◽  
Cancer Incidence ◽  
New South ◽  
New South Wales ◽  
Temporal Trends ◽  
Lung Cancer Incidence ◽  
South Wales

scholarly journals Intelligent Optimized Combined Model Based on GARCH and SVM for Forecasting Electricity Price of New South Wales, Australia

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Yi Yang ◽  
Yao Dong ◽  
Yanhua Chen ◽  
Caihong Li
Keyword(s):  
New South ◽  
Electrical Power ◽  
New South Wales ◽  
Garch Model ◽  
Electricity Price ◽  
Support Vector ◽  
Ant Colony Optimization Algorithm ◽  
Electrical Power System ◽  
Combined Model ◽  
South Wales

Daily electricity price forecasting plays an essential role in electrical power system operation and planning. The accuracy of forecasting electricity price can ensure that consumers minimize their electricity costs and make producers maximize their profits and avoid volatility. However, the fluctuation of electricity price depends on other commodities and there is a very complicated randomization in its evolution process. Therefore, in recent years, although large number of forecasting methods have been proposed and researched in this domain, it is very difficult to forecast electricity price with only one traditional model for different behaviors of electricity price. In this paper, we propose an optimized combined forecasting model by ant colony optimization algorithm (ACO) based on the generalized autoregressive conditional heteroskedasticity (GARCH) model and support vector machine (SVM) to improve the forecasting accuracy. First, both GARCH model and SVM are developed to forecast short-term electricity price of New South Wales in Australia. Then, ACO algorithm is applied to determine the weight coefficients. Finally, the forecasting errors by three models are analyzed and compared. The experiment results demonstrate that the combined model makes accuracy higher than the single models.

Gene Expression Programming and Machine Learning Methods for Bushfire Susceptibility Mapping in New South Wales, Australia

2021 ◽  
Author(s):  
Maryamsadat Hosseini ◽  
Samsung Lim
Keyword(s):  
Gene Expression ◽  
New South ◽  
Gene Expression Programming ◽  
Single Gene ◽  
New South Wales ◽  
Susceptibility Mapping ◽  
Support Vector ◽  
Ensemble Techniques ◽  
South Wales ◽  
Susceptibility Maps

Abstract Australia is one of the most bushfire-prone countries. Prediction and management of bushfires in bushfire-susceptible areas can reduce the negative impacts of bushfires. The generation of bushfire susceptibility maps can help improve the prediction of bushfires. The main aim of this study was to use single gene expression programming (GEP) and ensemble of GEP with well-known statistical methods to generate bushfire susceptibility maps for New South Wales, Australia as a case study. We used eight methods for bushfire susceptibility mapping: GEP, random forest (RF), support vector machine (SVM), frequency ratio (FR), ensemble techniques of GEP and FR (GEPFR), RF and FR (RFFR), SVM and FR (SVMFR), and LR and FR (LRFR). Areas under the curve (AUCs) of the receiver operating characteristic were used to evaluate the proposed methods. GEPFR exhibited the best performance for bushfire susceptibility mapping based on the AUC (0.890), while RFFR had the highest accuracy (94.70%) among the proposed methods. GEPFR is an ensemble method that uses features from the evolutionary algorithm and the statistical FR method, which results in a better AUC for the bushfire susceptibility maps. The ensemble methods had better performances than those of the single methods.

scholarly journals Frost Risk Management in Chickpea Using a Modelling Approach

Agronomy ◽  
2020 ◽  
Vol 10 (4) ◽  
pp. 460
Author(s):  
Yashvir S. Chauhan ◽  
Merrill Ryan
Keyword(s):  
New South ◽  
New South Wales ◽  
Temporal Trends ◽  
Yield Potential ◽  
Frost Risk ◽  
Modelling Framework ◽  
South Wales ◽  
Spatial And Temporal Trends ◽  
Reduced Water ◽  
Modelling Approach

Post-flowering frosts cause appreciable losses to the Australian chickpea industry. The Northern Grains Region (NGR) of Australia, which accounts for nearly 95% of chickpea production in Australia, is frequently subjected to such events. The objective of this study was to map frost risk in chickpea in the NGR and develop strategies to minimise the impacts of such risk. The Agricultural Production System Simulator (APSIM) modelling framework was used to determine spatial and temporal trends in post-flowering frost risk. The NGR could be divided into six broad sub-regions, each delineating locations with similar frost risk. The risk was nearly two to three times greater in the Southern Downs and Darling Downs sub-regions as compared to the Central Queensland Highlands, Dawson Callide, New South Wales, and Northern New South Wales–Western Downs sub-regions. There was an increasing trend in the frequency of frost events in the Southern Downs and New South Wales sub-regions, and a decreasing trend in the Central Queensland Highlands and Dawson Callide sub-regions, consistent with the changing climate of the NGR. In each sub-region, frost risk declined with delayed sowings, but such sowings resulted in simulation of reduced water limited yield potential (unfrosted) as well. The model output was also used to compute 10, 30, 50, and 70% probabilities of the last day of experiencing −3 to 2 °C minimum temperatures and identify the earliest possible sowings that would avoid such temperatures after flowering. Choosing the earliest sowing times with a 30% frost risk could help increase overall yields in environments with high frost risk. Simulations involving genotype x environment x management interactions suggested additional opportunities to minimise frost losses through the adoption of particular cultivars of differing phenology and the use of different agronomy in various environments of the NGR. The study indicates that there is considerable variation in frost risk across the NGR and that manipulating flowering times either through time of sowing or cultivar choice could assist in minimising yield losses in chickpea due to frost.

Decadal trends in shark catches and effort from the New South Wales, Australia, Shark Meshing Program 1950 - 2010

2011 ◽  
Vol 62 (6) ◽  
pp. 676 ◽  
Author(s):  
D. D. Reid ◽  
W. D. Robbins ◽  
V. M. Peddemors
Keyword(s):  
New South ◽  
New South Wales ◽  
Temporal Trends ◽  
Catch Per Unit Effort ◽  
Galeocerdo Cuvier ◽  
South Wales ◽  
Before And After ◽  
Large Animals ◽  
Size And Sex Composition ◽  
Over Time

The New South Wales (NSW) government has operated a program of netting beaches for the protection of swimmers and surfers against shark attack since 1937 in Sydney, and since 1949 in Newcastle and Wollongong. The scope and directives of the Shark Meshing Program have remained constant since its inception, with operational modifications in net specifications in 1972, changes in spatial deployment in 1972, 1987 and 1992, and the elimination of winter netting since 1989. This markedly increased meshing effort in 1972, and again in 1987. In the present study, we examine the trends in catch and effort for the period from 1950–1951 to 2009–2010 over this 200-km section of the NSW coast. Significant temporal trends in species, size and sex composition are described herein. Catches were consistently dominated by three shark taxa, hammerhead sharks (Sphyrna spp.), whaler sharks (Carcharhinus spp.) and Australian angel sharks (Squatina australis), although their relative contributions to catches varied over time. Catch per unit effort has significantly declined for five of the most abundant shark taxa over the study period, increasing only for a single taxon, the sevengill shark (Notorynchus cepedianus). Catches of larger, potentially dangerous white sharks (Carcharodon carcharias) and tiger sharks (Galeocerdo cuvier) saw fewer large animals being caught over time. This pattern was not observed across other taxa. Four different monthly trends were observed in landings of the most abundant eight taxa, reflecting differences in the biology of the catch species. The current study also provides useful information on catches and sizes of grey nurse (Carcharias taurus) and white sharks before and after their protection in NSW waters in 1984 and 1998, respectively.

The influence of fire and rainfall upon seedling recruitment in sand-mass (wallum) heathland of north-eastern New South Wales

2004 ◽  
Vol 52 (1) ◽  
pp. 93 ◽  
Author(s):  
S. J. Griffith ◽  
C. Bale ◽  
P. Adam
Keyword(s):  
Field Experiments ◽  
Seedling Recruitment ◽  
New South ◽  
Seedling Emergence ◽  
New South Wales ◽  
Temporal Trends ◽  
Plant Resource ◽  
South Wales ◽  
Fire Environment ◽  
North Eastern

Wallum heathland is extensive on coastal sand masses in north-eastern New South Wales and south-eastern Queensland. Here the climate is subtropical, although monthly rainfall is highly variable and unreliable. We examined the influence of fire and rainfall on seedling recruitment in bradysporous dry-heathland [Banksia aemula R.Br., Melaleuca nodosa (Sol. ex Gaertn.) Sm.] and wet-heathland [Banksia oblongifolia Cav., B.�ericifolia L.f. subsp. macrantha (A.S.George) A.S.George, Leptospermum liversidgei R.T.Baker and H.G. Sm.] species. Two specific questions were addressed: (1) do elevated levels of soil moisture facilitate seedling recruitment; (2) is the post-fire environment superior for seedling recruitment? Field experiments demonstrated that heathland species studied here are capable of successful recruitment in atypical habitat, and this proceeds irrespective of fire and unreliable rainfall. Conditions for growth and reproduction were found to be adequate if not more favourable in dry heathland, and this outcome included species usually associated with wet heathland. Spatial and temporal trends in seedling emergence and survival were examined in relation to post-fire predation and plant resource availability. Existing ideas about wallum management and conservation are evaluated, in particular the role of fire.

Effects of waterlogging and soil salinity on irrigated agriculture in the Murray Valley: a review

1986 ◽  
Vol 26 (6) ◽  
pp. 761 ◽  
Author(s):  
AM Grieve ◽  
E Dunford ◽  
D Marston ◽  
RE Martin ◽  
P Slavich
Keyword(s):  
Soil Salinity ◽  
White Clover ◽  
New South ◽  
New South Wales ◽  
Subterranean Clover ◽  
Economic Losses ◽  
Deep Drainage ◽  
Winter Cereals ◽  
South Wales ◽  
Loss Coefficients

A physical model was used to assess the effects of surface waterlogging and soil salinity on the productivity of winter cereals and irrigated dairy pastures on irrigation farms in the Berriquin and Wakool Irrigation Districts of the Murray Valley region of New South Wales. Parameters describing the physical properties of major soil types were combined with statistically derived estimates of rainfall excess over evapotranspiration to establish the incidence of waterlogging. Soils predisposed to waterlogging occupy 150000 ha of Berriquin District (45% of District) and 24 800 ha of Wakool District (73%). Estimates of yield losses from waterlogging ranged from 12.5% in annual subterranean clover-based pastures, 20% in winter cereals, to 25% for perennial ryegrass-white clover pastures. The relationships between yield and soil salinity were determined for barley, wheat, white clover, subterranean clover, and irrigated annual and perennial pastures growing under existing management practices in shallow watertable areas of the 2 Districts. Response functions were applied to soil salinity frequency distributions to derive production loss coefficients. Surveys showed that average soil salinities were lower in Berriquin than in Wakool. In 1984, 43% the soils in shallow watertable areas of Berriquin could be classed as saline, whereas, in 1982 the corresponding figure for Wakool was 72%. A further survey taken in 1984, 2 years after the inception of a deep drainage scheme, showed that saline soils in Wakool had decreased to 46% of the total area.We assessed economic losses associated with soil salinity and waterlogging by applying the derived loss coefficients to achievable yields for known production areas. Total annual losses for the 2 Districts exceeded $A13 million, or 16% of the 1984 value of the District's agricultural production. This figure underestimates real losses because we excluded livestock enterprises other than dairying, as well as summer cropping, from the study. Losses due to waterlogging ($A10 million overall) were more serious than those due to soil salinity (nearly $A4 million), particularly in Berriquin where shallow watertables were less extensive. In Wakool, 2 years' operation of the deep drainage scheme reduced losses due to soil salinity by $A750 000.Thus surface waterlogging and soil salinity cause serious economic losses in the irrigated areas of southern New South Wales. Research into appropriate techniques for on-farm irrigation management may reduce these losses, and delay further development of shallow watertables and soil salinisation, with sub of stantial economic and environmental benefits.

Sign in / Sign up

Export Citation Format

Share Document