Faisal Bin Ashraf
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Faisal Bin Ashraf has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Debjani Singh
Environmental Sciences Division Oak Ridge National Laboratory Oak Ridge TN USA
3 shared publications - Hannu Marttila
Water, Energy and Environmental Engineering Research Unit, University of Oulu, Oulu 90570, Finland
3 shared publications - Thomas A. Ruggles
Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA
3 shared publications Ali Torabi Haghighi
2 shared publications- Ali Torabi Haghighi
Water, Energy and Environmental Engineering Research Unit, Faculty of Technology, University of Oulu, 90014 Oulu, Finland
2 shared publications Artti Juutinen
2 shared publications
Latest Publications
- Open Access
- 16 June 2026
- Published by Elsevier in SSRN Electronic Journal
From Regulatory Text to Structured Data: A Domain-Specific LLM Framework for Extracting Hydropower Operational Constraints
Operational constraints governing hydropower facilities are buried in lengthy regulatory documents with inconsistent formatting, yet no scalable method exists to extract them. Here, we present a regulatory interpretation framework that pairs domain knowledge guided prompt engineering with multi-criteria evidence ranking system, implemented using openly available large language models (LLMs) deployable on local infrastructure. The framework utilizes expert regulatory reasoning, distinguishing mandated minimums from operational capabilities, resolving conflicting values across document sections, and producing traceable, audit-ready outputs (extracted value, regulatory context, and verbatim evidence) and applies it to U.S. Federal Energy Regulatory Commission (FERC) licenses and other hydropower regulatory documents. We evaluated four open LLMs, Llama 3.2 3B, Llama 3 8B, GPT-OSS 20B, and Llama 3.3 70B using a representative set of 50 hydropower regulatory documents across ten operational variables. For simple structured variables (project names, locations, generation capacity), the 70B model achieved 90-98% accuracy, while complex variables requiring interpretation of scattered regulatory text showed substantially lower performance (0-43% for zero-shot extraction). For a complex variable tested (minimum flow requirements), a targeted multi-stage extraction approach improved accuracy from 43% (zero-shot) to 76% (targeted). Overall accuracy across all ten variables was 52.7% (Correct + Partially Correct), with substantial variation by variable complexity. Among the four models tested, only the 70B model was able to follow the complex regulatory reasoning prompts; smaller models failed systematically via false negatives and hallucinations rather than reduced accuracy. The framework shifts regulatory data extraction from document-level classification to fact-level extraction with audit trail, substantially reducing expert effort.
- 16 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessFrom Regulatory Text to Structured Data: A Domain-Specific LLM Framework for Extracting Hydropower Operational Constraints
Operational constraints governing hydropower facilities are buried in lengthy regulatory documents with inconsistent formatting, yet no scalable method exists to extract them. Here, we present a regulatory interpretation framework that pairs domain knowledge guided prompt engineering with multi-criteria evidence ranking system, implemented using openly available large language models (LLMs) deployable on local infrastructure. The framework utilizes expert regulatory reasoning, distinguishing mandated minimums from operational capabilities, resolving conflicting values across document sections, and producing traceable, audit-ready outputs (extracted value, regulatory context, and verbatim evidence) and applies it to U.S. Federal Energy Regulatory Commission (FERC) licenses and other hydropower regulatory documents. We evaluated four open LLMs, Llama 3.2 3B, Llama 3 8B, GPT-OSS 20B, and Llama 3.3 70B using a representative set of 50 hydropower regulatory documents across ten operational variables. For simple structured variables (project names, locations, generation capacity), the 70B model achieved 90-98% accuracy, while complex variables requiring interpretation of scattered regulatory text showed substantially lower performance (0-43% for zero-shot extraction). For a complex variable tested (minimum flow requirements), a targeted multi-stage extraction approach improved accuracy from 43% (zero-shot) to 76% (targeted). Overall accuracy across all ten variables was 52.7% (Correct + Partially Correct), with substantial variation by variable complexity. Among the four models tested, only the 70B model was able to follow the complex regulatory reasoning prompts; smaller models failed systematically via false negatives and hallucinations rather than reduced accuracy. The framework shifts regulatory data extraction from document-level classification to fact-level extraction with audit trail, substantially reducing expert effort.
- Open Access
- 14 May 2026
- Published by Elsevier in Environmental Modelling & Software
- Vol. 203
Scaling open-weight large language models for hydropower regulatory information extraction: A systematic analysis
- 14 May 2026
- Published by Elsevier in Environmental Modelling & Software
- Vol. 203
Open AccessScaling open-weight large language models for hydropower regulatory information extraction: A systematic analysis
- Open Access
- 9 April 2026
- Published by Elsevier in SSRN Electronic Journal
From Regulatory Text to Structured Data: A Domain-Specific LLM Framework for Extracting Hydropower Operational Constraints
Operational constraints governing hydropower facilities are buried in lengthy regulatory documents with inconsistent formatting, yet no scalable method exists to extract them. Here, we present a regulatory interpretation framework that pairs domain knowledge guided prompt engineering with multi-criteria evidence ranking system, implemented using openly available large language models (LLMs) deployable on local infrastructure. The framework utilizes expert regulatory reasoning, distinguishing mandated minimums from operational capabilities, resolving conflicting values across document sections, and producing traceable, audit-ready outputs (extracted value, regulatory context, and verbatim evidence) and applies it to U.S. Federal Energy Regulatory Commission (FERC) licenses and other hydropower regulatory documents. We evaluated four open LLMs, Llama 3.2 3B, Llama 3 8B, GPT-OSS 20B, and Llama 3.3 70B using a representative set of 50 hydropower regulatory documents across ten operational variables. For simple structured variables (project names, locations, generation capacity), the 70B model achieved 90-98% accuracy, while complex variables requiring interpretation of scattered regulatory text showed substantially lower performance (0-43% for zero-shot extraction). For a complex variable tested (minimum flow requirements), a targeted multi-stage extraction approach improved accuracy from 43% (zero-shot) to 76% (targeted). Overall accuracy across all ten variables was 52.7% (Correct + Partially Correct), with substantial variation by variable complexity. Among the four models tested, only the 70B model was able to follow the complex regulatory reasoning prompts; smaller models failed systematically via false negatives and hallucinations rather than reduced accuracy. The framework shifts regulatory data extraction from document-level classification to fact-level extraction with audit trail, substantially reducing expert effort. The approach is transferable to other regulatory domains where critical information is dispersed across unstructured documents.
- 9 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessFrom Regulatory Text to Structured Data: A Domain-Specific LLM Framework for Extracting Hydropower Operational Constraints
Operational constraints governing hydropower facilities are buried in lengthy regulatory documents with inconsistent formatting, yet no scalable method exists to extract them. Here, we present a regulatory interpretation framework that pairs domain knowledge guided prompt engineering with multi-criteria evidence ranking system, implemented using openly available large language models (LLMs) deployable on local infrastructure. The framework utilizes expert regulatory reasoning, distinguishing mandated minimums from operational capabilities, resolving conflicting values across document sections, and producing traceable, audit-ready outputs (extracted value, regulatory context, and verbatim evidence) and applies it to U.S. Federal Energy Regulatory Commission (FERC) licenses and other hydropower regulatory documents. We evaluated four open LLMs, Llama 3.2 3B, Llama 3 8B, GPT-OSS 20B, and Llama 3.3 70B using a representative set of 50 hydropower regulatory documents across ten operational variables. For simple structured variables (project names, locations, generation capacity), the 70B model achieved 90-98% accuracy, while complex variables requiring interpretation of scattered regulatory text showed substantially lower performance (0-43% for zero-shot extraction). For a complex variable tested (minimum flow requirements), a targeted multi-stage extraction approach improved accuracy from 43% (zero-shot) to 76% (targeted). Overall accuracy across all ten variables was 52.7% (Correct + Partially Correct), with substantial variation by variable complexity. Among the four models tested, only the 70B model was able to follow the complex regulatory reasoning prompts; smaller models failed systematically via false negatives and hallucinations rather than reduced accuracy. The framework shifts regulatory data extraction from document-level classification to fact-level extraction with audit trail, substantially reducing expert effort. The approach is transferable to other regulatory domains where critical information is dispersed across unstructured documents.
- Open Access
- 15 March 2025
- Published by Copernicus GmbH
Evaluating approaches to identify winter heat wave events and their hydrological impacts in Sweden
While warm season heat waves are extensively studied, winter heat waves, which are extended periods of above-average temperature during winter months, largely remain overlooked. These events can disrupt typical water availability patterns and degrade water quality, particularly in regions already facing environmental stress.The identification of heat waves varies depending on the context and objective. For example, variable percentile thresholds are used to study heat wave mechanisms, while fixed temperature thresholds are often applied to assess their ecological impact. In the context of biogeochemical processes that govern contaminant retention and mobilization, variations in surface and groundwater flow can be particularly important.We analyzed the CAMELS‐SE dataset, which includes long-term observations of daily temperature, precipitation and streamflow from 1961 to 2020 across 50 sites in Sweden, along with local groundwater measurements, to identify and quantify heat-wave events using various approaches, and explore their correlation with observed surface and groundwater flow variability.The main objective of the study is to determine the timing, duration, frequency, and magnitude of winter heat waves in Sweden, and to assess trends in surface and groundwater flows associated with these events. We also explore whether certain specific geographical regions in Sweden are more vulnerable to the effects of winter heat waves.
- 15 March 2025
- Published by Copernicus GmbH
Open AccessEvaluating approaches to identify winter heat wave events and their hydrological impacts in Sweden
While warm season heat waves are extensively studied, winter heat waves, which are extended periods of above-average temperature during winter months, largely remain overlooked. These events can disrupt typical water availability patterns and degrade water quality, particularly in regions already facing environmental stress.The identification of heat waves varies depending on the context and objective. For example, variable percentile thresholds are used to study heat wave mechanisms, while fixed temperature thresholds are often applied to assess their ecological impact. In the context of biogeochemical processes that govern contaminant retention and mobilization, variations in surface and groundwater flow can be particularly important.We analyzed the CAMELS‐SE dataset, which includes long-term observations of daily temperature, precipitation and streamflow from 1961 to 2020 across 50 sites in Sweden, along with local groundwater measurements, to identify and quantify heat-wave events using various approaches, and explore their correlation with observed surface and groundwater flow variability.The main objective of the study is to determine the timing, duration, frequency, and magnitude of winter heat waves in Sweden, and to assess trends in surface and groundwater flows associated with these events. We also explore whether certain specific geographical regions in Sweden are more vulnerable to the effects of winter heat waves.
- 24 February 2025
- Published by Elsevier in Renewable Energy
- Vol. 244
Valued peaks: Sustainable water allocation for small hydropower plants in an era of explicit ecological needs
- 24 February 2025
- Published by Elsevier in Renewable Energy
- Vol. 244
Valued peaks: Sustainable water allocation for small hydropower plants in an era of explicit ecological needs
- Open Access
- 5 July 2024
- Published by Stockholm University Press in Tellus
- Vol. 76 (1) , 148-165
Compound Flooding in Halmstad: Common Causes, Interannual Variability and the Effects of Climate Change
Compound flooding was investigated in Halmstad on the Swedish west coast. The highest sea level ever recorded in Sweden was recorded by the Halmstad tide gauge. Moreover, through the city runs Nissan, one of the largest hydropower-producing rivers in southern Sweden. Together these features make the city an interesting location to study compound flooding. Co-variability between different hazards are studied using a unique set of downscaled climate scenario projections produced using state-of-the-art regional atmosphere, ocean and hydrological models. River discharge and sea level annual maxima are found to be correlated with peak strength on interannual time scales. This co-variability is found to derive from a mutual dependence that these hazards have on the North Atlantic Oscillation (NAO). Precipitation also shares this dependence in winter months and acts as a driver, building up the fluvial river hazard, while potentially adding additional pluvial hazard. Trends are also assessed, and it was found that future changes in compound flooding will most likely be driven primarily by mean sea level rise and secondarily by increases in mean river discharge.
- 5 July 2024
- Published by Stockholm University Press in Tellus
- Vol. 76 (1) , 148-165
Open AccessCompound Flooding in Halmstad: Common Causes, Interannual Variability and the Effects of Climate Change
Compound flooding was investigated in Halmstad on the Swedish west coast. The highest sea level ever recorded in Sweden was recorded by the Halmstad tide gauge. Moreover, through the city runs Nissan, one of the largest hydropower-producing rivers in southern Sweden. Together these features make the city an interesting location to study compound flooding. Co-variability between different hazards are studied using a unique set of downscaled climate scenario projections produced using state-of-the-art regional atmosphere, ocean and hydrological models. River discharge and sea level annual maxima are found to be correlated with peak strength on interannual time scales. This co-variability is found to derive from a mutual dependence that these hazards have on the North Atlantic Oscillation (NAO). Precipitation also shares this dependence in winter months and acts as a driver, building up the fluvial river hazard, while potentially adding additional pluvial hazard. Trends are also assessed, and it was found that future changes in compound flooding will most likely be driven primarily by mean sea level rise and secondarily by increases in mean river discharge.
- Open Access
- 15 December 2023
- Published by Elsevier in Science of The Total Environment
- Vol. 912, 169385
Nordic socio-recreational ecosystem services in a hydropeaked river
- 15 December 2023
- Published by Elsevier in Science of The Total Environment
- Vol. 912, 169385
Open AccessNordic socio-recreational ecosystem services in a hydropeaked river
- Open Access
- 27 November 2023
- Published by Wiley
Valued peaks: sustainable water allocation for small hydropower plants in an era of explicit ecological needs
Optimising hydropower operations to balance economic profitability and support functioning ecosystem services is integral to river management policy. In this article, we propose a multi-objective optimization framework for small hydropower plants (SHPs) to evaluate trade-offs among environmental flow scenarios. Specifically, we examine the balance between short-term losses in hydropower generation and the potential for compensatory benefits in the form of revenue from recreational ecosystem services, irrespective of the direct beneficiary. Our framework integrates a fish habitat model, a hydropower optimization model, and a recreational ecosystem service model to evaluate each environmental flow scenario. The optimisation process gives three outflow release scenarios, informed by previous streamflow realisations (dam inflow), and designed environmental flow constraints. The framework is applied and tested for the river Kuusinkijoki in North-eastern Finland, which is a habitat for migratory brown trout and grayling populations. We show that the revenue loss due to the environmental flow constraints arises through a reduction in revenue per generated energy unit and through a reduction in turbine efficiency. Additionally, the simulation results reveal that all the designed environmental flow constraints cannot be met simultaneously. Under the environmental flow scenario with both minimum flow and flow ramping rate constraints, the annual hydropower revenue decreases by 16.5%. An annual increase of 8% in recreational fishing visits offsets the revenue loss. The developed framework provides knowledge of the costs and benefits of hydropower environmental flow constraints and guides the prioritizing process of environmental measures.
- 27 November 2023
- Published by Wiley
Open AccessValued peaks: sustainable water allocation for small hydropower plants in an era of explicit ecological needs
Optimising hydropower operations to balance economic profitability and support functioning ecosystem services is integral to river management policy. In this article, we propose a multi-objective optimization framework for small hydropower plants (SHPs) to evaluate trade-offs among environmental flow scenarios. Specifically, we examine the balance between short-term losses in hydropower generation and the potential for compensatory benefits in the form of revenue from recreational ecosystem services, irrespective of the direct beneficiary. Our framework integrates a fish habitat model, a hydropower optimization model, and a recreational ecosystem service model to evaluate each environmental flow scenario. The optimisation process gives three outflow release scenarios, informed by previous streamflow realisations (dam inflow), and designed environmental flow constraints. The framework is applied and tested for the river Kuusinkijoki in North-eastern Finland, which is a habitat for migratory brown trout and grayling populations. We show that the revenue loss due to the environmental flow constraints arises through a reduction in revenue per generated energy unit and through a reduction in turbine efficiency. Additionally, the simulation results reveal that all the designed environmental flow constraints cannot be met simultaneously. Under the environmental flow scenario with both minimum flow and flow ramping rate constraints, the annual hydropower revenue decreases by 16.5%. An annual increase of 8% in recreational fishing visits offsets the revenue loss. The developed framework provides knowledge of the costs and benefits of hydropower environmental flow constraints and guides the prioritizing process of environmental measures.
- Open Access
- 29 December 2021
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 58 (1)
A Method for Assessment of Sub‐Daily Flow Alterations Using Wavelet Analysis for Regulated Rivers
New tools are needed to evaluate the impacts of short‐term hydropower regulation practices on downstream river systems and to progress towards sustainable river‐flow management. As hydropower is increasingly being used to balance the energy load deficit caused by other less flexible sources, sub‐daily flow conditions across many regulated river (RR) systems are changing. To address this, we used wavelet analyses to quantify the discharge variability in RRs and categorized the level of variability based on the conditions in natural free‐flowing rivers. The presented framework used the definition of fluvial connectivity (Grill et al., 2019) to identify free‐flowing rivers used in the study. We tested the developed framework in 12 different RRs in Finland and found higher overall averaged subdaily variations, with up to 20 times larger variability than natural conditions. A large, highly regulated Finnish river system was found to have the highest sub‐daily variations in winter, while smaller RRs with lower levels of regulation the highest variations in summer. The proposed framework offers a novel tool for sustainable river management and can be easily applied to various rivers and regions globally. It had flexibility to analyze sub‐daily variations in desired seasonal or other ecologically sensitive periods.
- 29 December 2021
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 58 (1)
Open AccessA Method for Assessment of Sub‐Daily Flow Alterations Using Wavelet Analysis for Regulated Rivers
New tools are needed to evaluate the impacts of short‐term hydropower regulation practices on downstream river systems and to progress towards sustainable river‐flow management. As hydropower is increasingly being used to balance the energy load deficit caused by other less flexible sources, sub‐daily flow conditions across many regulated river (RR) systems are changing. To address this, we used wavelet analyses to quantify the discharge variability in RRs and categorized the level of variability based on the conditions in natural free‐flowing rivers. The presented framework used the definition of fluvial connectivity (Grill et al., 2019) to identify free‐flowing rivers used in the study. We tested the developed framework in 12 different RRs in Finland and found higher overall averaged subdaily variations, with up to 20 times larger variability than natural conditions. A large, highly regulated Finnish river system was found to have the highest sub‐daily variations in winter, while smaller RRs with lower levels of regulation the highest variations in summer. The proposed framework offers a novel tool for sustainable river management and can be easily applied to various rivers and regions globally. It had flexibility to analyze sub‐daily variations in desired seasonal or other ecologically sensitive periods.