16 results on '"Ghahramani, Afshin"'
Search Results
2. Deep learning hybrid model with Boruta-Random forest optimiser algorithm for streamflow forecasting with climate mode indices, rainfall, and periodicity
- Author
-
Masrur Ahmed, A.A., Deo, Ravinesh C., Feng, Qi, Ghahramani, Afshin, Raj, Nawin, Yin, Zhenliang, and Yang, Linshan
- Published
- 2021
- Full Text
- View/download PDF
3. Effect of ground cover on splash and sheetwash erosion over a steep forested hillslope: A plot-scale study
- Author
-
Ghahramani, Afshin, Ishikawa, Yoshiharu, Gomi, Takashi, Shiraki, Katsushige, and Miyata, Shusuke
- Published
- 2011
- Full Text
- View/download PDF
4. Classification of catchments for nitrogen using Artificial Neural Network Pattern Recognition and spatial data
- Author
-
O'Sullivan, Cherie M., Ghahramani, Afshin, Deo, Ravinesh C., Pembleton, Keith, Khan, Urooj, Tuteja, Narendra, O'Sullivan, Cherie M., Ghahramani, Afshin, Deo, Ravinesh C., Pembleton, Keith, Khan, Urooj, and Tuteja, Narendra
- Abstract
In hydrological modelling, classification of catchments is a fundamental task for overcoming deficits in observational datasets. Most attention on this issue has focussed on identifying the catchments with similar hydrological responses for streamflow. Yet, effective methods for catchment classification are currently lacking in respect to Dissolved Inorganic Nitrogen (DIN), a water quality constituent that, at increasing concentrations, is threatening nutrient sensitive environment. Pattern recognition, using standard Artificial Neural Network algorithm is applied, as a novel approach to classify datasets that are considered to be suitable proxies for biological and anthropogenic drivers of observed DIN releases. Eleven gauged Great Barrier Reef (GBR) catchments within Queensland Australia are classified using spatial datasets extracted from ecosystem (e.g. original ecosystem responses to biogeographic, land zone, land form, and soil type attributes) and land use maps. To evaluate the performance of the examined spatial datasets as a proxy for deductive classification, the classification process is repeated inductively, using observed DIN and streamflow data from gauging stations. The ANN-PR method is seen to generate the same classification score format for the differing dataset types, and this facilitates a direct comparison for model output for observed data corroborations. The Kruskal-Wallis test for independence, at p > 0.05, identifies the deductive classification approach as a predictor for classification using DIN observations, which lacks an independence from each other at a p value of 0.01 and 0.02. This study concludes that an ANN-PR method can integrate the ecosystem and land use mapping data to deductively classify the GBR catchments into four regions that also have similar patterns of DIN concentrations. Due to the uniform availability of the mapping data, the findings provide a sound basis for further investigations into the transposing of knowledge f
- Published
- 2021
5. Transformative and systemic climate change adaptations in mixed crop-livestock farming systems.
- Author
-
Ghahramani, Afshin and Bowran, David
- Subjects
- *
CLIMATE change , *AGRICULTURE , *CROP management , *LAND use , *SUSTAINABILITY - Abstract
Mixed crop-livestock farming systems provide food for more than half of the world's population. These agricultural systems are predicted to be vulnerable to climate change and therefore require transformative adaptations. In collaboration with farmers in the wheatbelt of Western Australia (WA), a range of systemic and transformative adaptation options, e.g. land use change, were designed for the modelled climate change projected to occur in 2030 (0.4–1.4° increase in mean temperature). The effectiveness of the adaptation options was evaluated using coupled crop and livestock biophysical models within an economic and environmental framework at both the enterprise and farm scales. The relative changes in economic return and environmental variables in 2030 are presented in comparison with a baseline period (1970–2010). The analysis was performed on representative farm systems across a rainfall transect. Under the impact of projected climate change, the economic returns of the current farms without adaptation declined by between 2 and 47%, with a few exceptions where profit increased by up to 4%. When the adaptations were applied for 2030, profit increased at the high rainfall site in the range between 78 and 81% through a 25% increase in the size of livestock enterprise and adjustment in sowing dates, but such profit increases were associated with 6–10% increase in greenhouse gas (GHG) emissions. At the medium rainfall site, a 100% increase in stocking rate resulted in 5% growth in profit but with a 61–71% increase in GHG emissions and the increased likelihood of soil degradation. At the relatively low rainfall site, a 75% increase in livestock when associated with changes in crop management resulted in greater profitability and a smaller risk of soil erosion. This research identified that a shift toward a greater livestock enterprises (stocking rate and pasture area) could be a profitable and low-risk approach and may have most relevance in years with extremely low rainfall. If transformative adaptations are adopted then there will be an increased requirement for an emissions control policy due to livestock GHG emissions, while there would be also need for soil conservation strategies to be implemented during dry periods. The adoption rate analysis with producers suggests there would be a greater adoption rate for less intensified adaptations even if they are transformative. Overall the current systems would be more resilient with the adaptations, but there may be challenges in terms of environmental sustainability and in particular with soil conservation. [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
6. Pattern recognition describing spatio-temporal drivers of catchment classification for water quality.
- Author
-
O'Sullivan, Cherie M., Ghahramani, Afshin, Deo, Ravinesh C., and Pembleton, Keith G.
- Published
- 2023
- Full Text
- View/download PDF
7. Impact of climate changes on existing crop-livestock farming systems.
- Author
-
Ghahramani, Afshin and Moore, Andrew D.
- Subjects
- *
AGRICULTURAL industries , *CLIMATE change , *AGRICULTURE , *LIVESTOCK productivity , *SIMULATION methods & models , *CROP yields - Abstract
The state of Western Australia is a major producer and exporter of crops and livestock. Mixed farming systems are typical agricultural enterprises in the Western Australian wheatbelt where climate drives the productivity and profitability of these farms and therefore the effects of likely climate change on their performance need to be understood. Here the effects of climate change projected at 2030 were evaluated compared to a baseline period (1980–1999) on mixed farming systems at paddock, enterprise and whole farm scales using the coupled APSIM and GRAZPLAN biophysical simulation models. The yield of different crops, livestock production and gross margins were assessed under current and projected climates using current farming technology and management practices. Representative mixed-farm systems were selected along a climate transect. Modelling analysis suggests that current production levels and gross margins of mixed farm systems in Western Australia will not be sustained in 2030 climate conditions except in areas of moderately high-rainfall. Whole farm gross margin declined at all site × potential climate scenarios between 1% and 22% except in moderately high rainfall where gross margin increased by up to 4% under a ‘hot and moderate change in rainfall’ climate. Projected crop yields declined for most of the crop × site × potential climate combinations, with greatest declines under a hot and dry climate (at driest margin of transect) in which wheat, barley, canola, and lupin yield declined up to 16%, 15%, 21%, and 27%, respectively. Increase in yield was predicted for wheat and barley at some of the site × potential climate s. Wheat yield increased only under moderately high rainfall region by 6% while barley increased by 1%. Simulated cropping gross margin was also shown to decline by between > 1% and 23%, except for the moderately high-rainfall site where cropping gross margins were projected to increase by up to 3%. Changes in simulated livestock production were smaller and less variable than for crop production. The change in weight of livestock sold across sites × potential climate combinations ranged between − 3% and + 3%. Livestock gross margin varied between − 11% and + 6%. Modelling results indicated a greater fertilisation effect of the elevated CO 2 on pasture production than on crop yield and biomass particularly in drier sites. But however, this could not offset negative impact of climate change under hot potential climates. The main negative environmental impacts from the projected climate change were declines in annual net primary production (ANPP), ground cover and water use efficiency mostly at drier sites. Whole farm N 2 O emission declined significantly for the majority of site × potential climate combinations, while smaller decreases in ruminant CH 4 emission were predicted. In 2030, returns from livestock enterprises are predicted to be smaller, but less variable than from cropping and with increasing probability of success in drier regions. Reduced variability in financial return is important from the perspective of whole farm risk management. Shifts in enterprise mix in dryland mixed-farming systems towards increased livestock may be a helpful strategy in adapting to climate change and managing the associated financial risks. [ABSTRACT FROM AUTHOR]
- Published
- 2016
- Full Text
- View/download PDF
8. The value of adapting to climate change in Australian wheat farm systems: farm to cross-regional scale.
- Author
-
Ghahramani, Afshin, Kokic, Philip N., Moore, Andrew D., Zheng, Bangyou, Chapman, Scott C., Howden, Mark S., and Crimp, Steven J.
- Subjects
- *
CLIMATE change , *WHEAT farming , *AGRICULTURAL climatology , *AGRICULTURAL productivity , *CROP yields - Abstract
Wheat is one of the main grains produced across the globe and wheat yields are sensitive to changes in climate. Australia is a major exporter of wheat, and variations in its national production influence trade supplies and global markets. We evaluated the effect of climate change in 2030 compared to a baseline period (1980–1999) by upscaling from farm to the national level. Wheat yields and gross margins under current and projected climates were assessed using current technology and management practices and then compared with ‘best adapted’ yield achieved by adjustments to planting date, nitrogen fertilizer, and available cultivars for each region. For the baseline climate (1980–1999), there was a potential yield gap modelled as optimized adaptation gave potential up scaled yields (tonne/ha) and gross margins (AUD$/ha) of 17% and 33% above the baseline, respectively. In 2030 and at Australian wheatbelt level, climate change impact projected to decline wheat yield by 1%. For 2030, national wheat yields were simulated to decrease yields by 1% when using existing technology and practices but increase them by 18% assuming optimal adaptation. Hence, nationally at 2030 for a fully-adapted wheat system, yield increased by 1% and gross margin by 0.3% compared to the fully adapted current climate baseline. However, there was substantial regional variation with median yields and gross margins decreasing in 55% of sites. Full adaptation of farm systems under current climate is not expected, and so this will remain an on-going challenge. However, by 2030 there will be a greater opportunity to increase the overall water use and nitrogen efficiencies of the Australian wheat belt, mostly resulting from elevated atmospheric CO 2 concentrations. [ABSTRACT FROM AUTHOR]
- Published
- 2015
- Full Text
- View/download PDF
9. Systemic adaptations to climate change in southern Australian grasslands and livestock: Production, profitability, methane emission and ecosystem function.
- Author
-
Ghahramani, Afshin and Moore, Andrew D.
- Subjects
- *
AGRICULTURAL climatology , *PLANT adaptation , *AGRICULTURAL productivity , *METHANE & the environment , *PROFITABILITY , *GRASSLANDS , *LIVESTOCK - Abstract
The annual net primary production (ANPP) of temperate grasslands and production of livestock industries is predicted to decrease in southern Australia with future climate change. By using biophysical modelling, we address productivity and profitability of grazing systems while considering systemic combination of grassland management and animal genetic improvement options. Single incremental adaptations will not completely avert declines in productivity and profitability; hence, combinations of adaptations are needed. The synergistic effects of these adaptations could potentially offset decreasing production and profit in 2030 over the majority of southern Australia, but not in some drier regions after 2030. These results demonstrate the need for changes in strategies over time with greater complexity of adaptations in drier regions. Upscaling over all southern Australia, financially optimal systemic combination (fully enhanced systems) could increase profit by 68.61%, 68.63% and 50.81% in 2030, 2050, and 2070, compared to the production of the historical period with current farm system management. Financially-motivated changes to grazing systems will result in improvement in grassland health, soil environment, and water use efficiency. However, full adaption of systemic adaptation will lead to greater ruminant CH4 emission from 70?kg ha-1?yr-1 in baseline (1970-1999) to 84, 83, and 75?kg ha-1?yr-1 in 2030, 2050, and 2070. Higher rates of CH4 emissions may affect profitability depending on future emissions pricing. In most of the drier regions, greater input intensity and management complexity may be required which requirement is likely to increase over time. However some of the drier regions would still require transformative adaptations. [ABSTRACT FROM AUTHOR]
- Published
- 2015
- Full Text
- View/download PDF
10. Classification of catchments for nitrogen using Artificial Neural Network Pattern Recognition and spatial data.
- Author
-
O'Sullivan, Cherie M., Ghahramani, Afshin, Deo, Ravinesh C., Pembleton, Keith, Khan, Urooj, and Tuteja, Narendra
- Published
- 2022
- Full Text
- View/download PDF
11. A pragmatic parameterisation and calibration approach to model hydrology and water quality of agricultural landscapes and catchments.
- Author
-
Ghahramani, Afshin, Freebairn, David M., Sena, Dipaka R., Cutajar, Justin L., and Silburn, David M.
- Subjects
- *
WATER quality , *AGRICULTURAL landscape management , *WATER quality management , *HYDROLOGIC models , *LAND management - Abstract
Australian and Queensland Government's Reef 2050 Water Quality Improvement Plan has set targets for improving the water quality entering the Great Barrier Reef lagoon. Given the large public investment and the deficit of data linking on-farm land management to changes in environmental outcomes, there is a need for a robust and efficient methods of quantifying links between land management and water quality. This paper explores a pragmatic approach to making this link using available data. We demonstrate that a simple parameterisation process is suitable for estimating hydrology and water quality across a wide range of land uses and management practices in agricultural landscapes. However, a manually calibrated model may still require the analysis of parameters to reduce error variances and evaluate uncertainties. Confidence in estimating hydrology and water quality in descending order is: runoff, sediment, nitrogen, phosphorous, and pesticide losses, reflecting the availability of data and inherent error propagation. • A pragmatic modelling by Howleaky is suitable to link management to water quality. • A manually calibrated model may still require a reduction in error variances. • Data availability and inherent error propagation determined confidence in modelling. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
12. Land use change in Australian mixed crop-livestock systems as a transformative climate change adaptation.
- Author
-
Ghahramani, Afshin, Kingwell, Ross S., and Maraseni, Tek Narayan
- Subjects
- *
LAND use , *CLIMATE change , *RANGELANDS , *CROPPING systems , *INDUSTRIAL policy , *PASTURES , *PHYSIOLOGICAL adaptation , *FINANCIAL risk - Abstract
Mixed crop-livestock farming systems provide food for over half of the global population. However, some important food exporting countries, like Australia, are predicted to be vulnerable to climate change and may require transformative adaptations if they are to continue their role in food exportation. This paper assesses the potential impacts of projected climate change by 2030 (0.4–1.6° increase in mean temperature) on Australian mixed crop-livestock systems and examines the consequences of shifts in land allocations to cropping and grazing, in these systems, as an adaptation option. Farm bio-economic simulation models were developed for these mixed enterprise systems in several regions of Australia. These models were based on biophysically coupled crop, pasture, and livestock simulation models that in turn drew on site-based downscaled climate projection datasets. The farm models calculated farm profitability and risk measures. A range of land use changes was investigated. At drier locations facing adverse climate change, results showed a transition towards a greater emphasis on livestock production could be beneficial when assessed against multiple criteria of farm profit, downside financial risk, and environmental damage. We highlight some industry and government actions and policies that could facilitate these preferred adaptation strategies at such locations. • Temperature increase of 0.4–1.6° affect mixed crop-livestock systems in Australia. • Transition towards a greater emphasis on livestock production is often desirable. • Financially optimal land allocations vary between historical and future climate. • Increase in the land devoted to pasture is a strategy to manage future climate risk. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
13. New double decomposition deep learning methods for river water level forecasting.
- Author
-
Ahmed, A.A. Masrur, Deo, Ravinesh C., Ghahramani, Afshin, Feng, Qi, Raj, Nawin, Yin, Zhenliang, and Yang, Linshan
- Published
- 2022
- Full Text
- View/download PDF
14. The chaos in calibrating crop models: Lessons learned from a multi-model calibration exercise.
- Author
-
Wallach, Daniel, Palosuo, Taru, Thorburn, Peter, Hochman, Zvi, Gourdain, Emmanuelle, Andrianasolo, Fety, Asseng, Senthold, Basso, Bruno, Buis, Samuel, Crout, Neil, Dibari, Camilla, Dumont, Benjamin, Ferrise, Roberto, Gaiser, Thomas, Garcia, Cecile, Gayler, Sebastian, Ghahramani, Afshin, Hiremath, Santosh, Hoek, Steven, and Horan, Heidi
- Subjects
- *
CALIBRATION , *PARAMETER estimation , *CROPS , *PHENOLOGY - Abstract
Calibration, the estimation of model parameters based on fitting the model to experimental data, is among the first steps in many applications of process-based models and has an important impact on simulated values. We propose a novel method of developing guidelines for calibration of process-based models, based on development of recommendations for calibration of the phenology component of crop models. The approach was based on a multi-model study, where all teams were provided with the same data and asked to return simulations for the same conditions. All teams were asked to document in detail their calibration approach, including choices with respect to criteria for best parameters, choice of parameters to estimate and software. Based on an analysis of the advantages and disadvantages of the various choices, we propose calibration recommendations that cover a comprehensive list of decisions and that are based on actual practices. • We propose a new approach to calibration recommendations for process-based models. • Approach is based on analyzing calibration in multi-model simulation exercises. • Resulting recommendations are holistic and anchored in actual practice. • We derive calibration recommendations for crop models used to simulate phenology. • Recommendations concern: objective function, parameters to estimate, software used. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
15. Assessing the hydraulic reduction performance of HYDRUS-1D for application of alkaline irrigation in variably-saturated soils: Validation of pH driven hydraulic reduction scaling factors.
- Author
-
Ali, Aram, Bennett, John McL, Biggs, Andrew A.J., Marchuk, Alla, and Ghahramani, Afshin
- Subjects
- *
ACID soils , *SOIL acidity , *HYDRAULIC conductivity , *SOIL profiles , *SODIC soils , *ALKALI lands - Abstract
Land application of alkaline irrigation water is an increasing practice in most agricultural lands around the world due to the shortage of freshwater resources. Accurate evaluation of the effects of alkalinity on soil properties is essential to avoid environmental risks. In this study, we used long leaching columns to evaluate alkalinisation and sodification hazards in soils in the laboratory at different water qualities (0, 100, 310 and 650 HCO 3 -, mg L−1) with electrical conductivity (EC) ≈ 2.1 dS m−1 and sodium adsorption ratio (SAR) ≈ 12 (mmol c L−1)0.5. The ability of the HYDRUS-1D model to simulate solute and water movement under unsaturated conditions in columns of 40 cm height filled with acidic, neutral or alkaline soils was also assessed. Changes in soil EC, SAR, pH and alkalinity were monitored at 5, 15, 25 and 35 cm depths for 290 days. Increased solution alkalinity resulted in increased pH, alkalinity and sodicity within the soil profile, in particular for the soil surface and acidic soils. In general, the HYDRUS model, using the standard hydraulic reduction scaling factor, was able to simulate the effects of alkalinity in the soil profile and the associated hydraulic conductivity reduction. Amending the pH driven hydraulic reduction scaling factor in the model to a non-linear, soil-specific, pedotransfer function significantly improved the correlation between predicted and observed hydraulic conductivity. The findings of this study provide validation for a non-linear approach towards determining the pH hydraulic reduction scaling factor in the HYDRUS-1D model for unsaturated conditions. However, it is noted that further improvement of this non-linear approach is required to incorporate other factors governing soil structural stability. • The pedotransfer hydraulic reduction function significantly improves hydraulic reduction prediction. • The pH and alkalinity (HCO 3 -) are the primary drivers of model variability. • The current standard hydraulic conductivity reduction in HYDRUS model requires improvement. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
16. How well do crop modeling groups predict wheat phenology, given calibration data from the target population?
- Author
-
Wallach, Daniel, Palosuo, Taru, Thorburn, Peter, Gourdain, Emmanuelle, Asseng, Senthold, Basso, Bruno, Buis, Samuel, Crout, Neil, Dibari, Camilla, Dumont, Benjamin, Ferrise, Roberto, Gaiser, Thomas, Garcia, Cécile, Gayler, Sebastian, Ghahramani, Afshin, Hochman, Zvi, Hoek, Steven, Hoogenboom, Gerrit, Horan, Heidi, and Huang, Mingxia
- Subjects
- *
PHENOLOGY , *CALIBRATION , *MEASUREMENT errors , *WHEAT , *CROP management - Abstract
• 27 modeling groups were evaluated for wheat phenology predictions for France. • Calibration and evaluation data were sampled from the same target population. • The calibration and evaluation data have neither year nor site in common. • The best groups had a mean absolute error comparable to the measurement error. • Model structure alone does not determine prediction accuracy. Predicting phenology is essential for adapting varieties to different environmental conditions and for crop management. Therefore, it is important to evaluate how well different crop modeling groups can predict phenology. Multiple evaluation studies have been previously published, but it is still difficult to generalize the findings from such studies since they often test some specific aspect of extrapolation to new conditions, or do not test on data that is truly independent of the data used for calibration. In this study, we analyzed the prediction of wheat phenology in Northern France under observed weather and current management, which is a problem of practical importance for wheat management. The results of 27 modeling groups are evaluated, where modeling group encompasses model structure, i.e. the model equations, the calibration method and the values of those parameters not affected by calibration. The data for calibration and evaluation are sampled from the same target population, thus extrapolation is limited. The calibration and evaluation data have neither year nor site in common, to guarantee rigorous evaluation of prediction for new weather and sites. The best modeling groups, and also the mean and median of the simulations, have a mean absolute error (MAE) of about 3 days, which is comparable to the measurement error. Almost all models do better than using average number of days or average sum of degree days to predict phenology. On the other hand, there are important differences between modeling groups, due to model structural differences and to differences between groups using the same model structure, which emphasizes that model structure alone does not completely determine prediction accuracy. In addition to providing information for our specific environments and varieties, these results are a useful contribution to a knowledge base of how well modeling groups can predict phenology, when provided with calibration data from the target population. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.