Advanced search in
Research products
arrow_drop_down
Searching FieldsTerms
Any field
arrow_drop_down
includes
arrow_drop_down
Include:
4 Research products, page 1 of 1

  • Other research products
  • 2018-2022
  • Open Access
  • IE
  • Energy Research
  • Rural Digital Europe

Date (most recent)
arrow_drop_down
  • Open Access English
    Authors: 
    Kenny, Eoin M.; Ruelle, Elodie; Geoghegan, Anne; Temraz, Mohammed; Keane, Mark T.; et al.;
    Country: Ireland

    The 29th International Joint Conference on Artificial Intelligence - 17th Pacific Rim International Conference on Artificial Intelligence (IJCAI-PRICAI-20), Yokohama, Japan, January 2021 (Conference postponed due to COVID-19 pandemic) Smart agriculture (SmartAg) has emerged as a rich domain for AI-driven decision support systems (DSS); however, it is often challenged by user-adoption issues. This paper reports a case-based reasoning system, PBI-CBR, that predicts grass growth for dairy farmers, that combines predictive accuracy and explanations to improve user adoption. PBI-CBR’s key novelty is its use of Bayesian methods for case-base maintenance in a regression domain. Experiments report the tradeoff between predictive accuracy and explanatory capability for different variants of PBI-CBR, and how updating Bayesian priors each year improves performance. Science Foundation Ireland Insight Research Centre

  • Open Access English
    Authors: 
    Lundholm, Anders; Corrigan, Edwin; Nieuwenhuis, Maarten;
    Country: Ireland

    The Environmental and Sustainable Resource Management (ESRM) Post-graduate Research Day, University College Dublin, Ireland, 6 December 2019 The inherent factor of poor site productivity in western peatland forests combined with the reduction in management intensity from increased environmental considerations has brought some new challenges into forest management. Our study investigates new, alternative forest management models in the area chosen for this study, Cloosh forest, Co. Galway, to assess how these forests should be managed under future impacts of climate change and dynamic timber prices due to an expanding bioeconomy, and to quantify the impact this will have on forest ecosystem services (ES). Department of Agriculture, Food and the Marine European Commission Horizon 2020

  • Open Access English
    Authors: 
    Thomas, Ian; Bruen, Michael; Mockler, Eva M.; Kelly, Edel; Murphy, Paul; et al.;
    Country: Ireland

    LUWQ 2019: International Interdisciplinary Conference on Land Use and Water Quality. Agriculture and the Environment. Aarhus, Denmark, 3-6 June 2019 Policymakers, farm advisors and water agencies require up-to-date national maps of critical source areas (CSAs) of nitrogen (N) and phosphorus (P) losses from agricultural land to improve catchment management decisions. The DiffuseTools project aimed to achieve this in Ireland by updating the existing Catchment Characterisation Tool and sub-model NCYCLE_IRL, which predicts environmental losses of N and P from the farm via surface runoff, leaching, denitrification and volatilisation. Updates included (i) using improved national maps of farm-scale source loadings as inputs, (ii) sub-field scale modelling of surface transport risk using soil topographic indices derived from 1 m and 5 m NEXTMap digital elevation models (DEMs), (iii) modelling hydrological disconnectivity from microtopography (HSA Index) and reinfiltration (SCIMAP), (iv) improving the national ditch and stream channel network used by the model by DEM extraction, and (v) using SCIMAP to improve predictions of erosion risk. The improved national source loading maps included mean nationally weighted farm-gate N and P imports (fertilizer, feed and livestock) and balance surpluses (kg/ha) calculated for each stocking rate and soil group (land use potential) category within each sector type (dairy, mixed livestock, suckler cattle, non-suckler cattle, sheep and tillage), using annual Teagasc National Farm Survey data (2008-15). Furthermore, updated national maps of soil P and atmospheric N and P deposition inputs were also used within the national source loading maps to improve model performance. National CSA maps for N and P for each pathway were then produced and evaluated using water quality monitoring data and field observations from the Environmental Protection Agency and Teagasc Agricultural Catchments Programme. These maps will be able to support sustainable intensification by informing farm and catchment management decisions such as where to cost effectively target mitigation measures to reduce environmental losses, where to distribute nutrient surpluses (to non-CSAs in nutrient deficit), and improving functional land management. Environmental Protection Agency Check for published version during checkdate report - AC

  • Open Access English
    Authors: 
    Bampoulas, Adamantio; Saffari, Mohhamad; Pallonetto, Fabiano; Mangina, Eleni; Finn, Donal;
    Publisher: IEEE
    Country: Ireland

    The 2019 IEEE 5th World Forum on Internet of Things (WF-IoT), Limerick, Ireland, 15-18 April 2019 This paper provides a research plan focusing on the application of self-learning techniques for energy systems integration in the residential building sector. Demand response is becoming increasingly important in the evolution of the power grid since demand no longer necessarily determines system supply but is now more closely constrained by generation profiles. Demand response can offer energy flexibility services across wholesale and balancing markets. Different applications have focused on the Internet of Things in demand response to assist customers, aggregators and utility companies to manage the energy consumption and energy usage through the adjustment of consumer behaviour. Even though there is extensive work in the literature regarding the potential of the commercial and the residential building sectors to provide flexibility, to date there is no standardised framework to evaluate this flexibility in a customer-Tailored way. At the same time, demand response events may affect occupant comfort expectations hindering the utilisation of flexibility that building energy systems can provide. In this research, the integration of machine learning algorithms into building control systems is investigated, in order to unify the monitoring and control of the separate systems under a holistic approach. This will allow the operation of the systems to be optimised with respect to reducing their energy consumption and their environmental footprint in tandem with the maximisation of flexibility, while maintaining occupant comfort. Science Foundation Ireland

Advanced search in
Research products
arrow_drop_down
Searching FieldsTerms
Any field
arrow_drop_down
includes
arrow_drop_down
Include:
4 Research products, page 1 of 1
  • Open Access English
    Authors: 
    Kenny, Eoin M.; Ruelle, Elodie; Geoghegan, Anne; Temraz, Mohammed; Keane, Mark T.; et al.;
    Country: Ireland

    The 29th International Joint Conference on Artificial Intelligence - 17th Pacific Rim International Conference on Artificial Intelligence (IJCAI-PRICAI-20), Yokohama, Japan, January 2021 (Conference postponed due to COVID-19 pandemic) Smart agriculture (SmartAg) has emerged as a rich domain for AI-driven decision support systems (DSS); however, it is often challenged by user-adoption issues. This paper reports a case-based reasoning system, PBI-CBR, that predicts grass growth for dairy farmers, that combines predictive accuracy and explanations to improve user adoption. PBI-CBR’s key novelty is its use of Bayesian methods for case-base maintenance in a regression domain. Experiments report the tradeoff between predictive accuracy and explanatory capability for different variants of PBI-CBR, and how updating Bayesian priors each year improves performance. Science Foundation Ireland Insight Research Centre

  • Open Access English
    Authors: 
    Lundholm, Anders; Corrigan, Edwin; Nieuwenhuis, Maarten;
    Country: Ireland

    The Environmental and Sustainable Resource Management (ESRM) Post-graduate Research Day, University College Dublin, Ireland, 6 December 2019 The inherent factor of poor site productivity in western peatland forests combined with the reduction in management intensity from increased environmental considerations has brought some new challenges into forest management. Our study investigates new, alternative forest management models in the area chosen for this study, Cloosh forest, Co. Galway, to assess how these forests should be managed under future impacts of climate change and dynamic timber prices due to an expanding bioeconomy, and to quantify the impact this will have on forest ecosystem services (ES). Department of Agriculture, Food and the Marine European Commission Horizon 2020

  • Open Access English
    Authors: 
    Thomas, Ian; Bruen, Michael; Mockler, Eva M.; Kelly, Edel; Murphy, Paul; et al.;
    Country: Ireland

    LUWQ 2019: International Interdisciplinary Conference on Land Use and Water Quality. Agriculture and the Environment. Aarhus, Denmark, 3-6 June 2019 Policymakers, farm advisors and water agencies require up-to-date national maps of critical source areas (CSAs) of nitrogen (N) and phosphorus (P) losses from agricultural land to improve catchment management decisions. The DiffuseTools project aimed to achieve this in Ireland by updating the existing Catchment Characterisation Tool and sub-model NCYCLE_IRL, which predicts environmental losses of N and P from the farm via surface runoff, leaching, denitrification and volatilisation. Updates included (i) using improved national maps of farm-scale source loadings as inputs, (ii) sub-field scale modelling of surface transport risk using soil topographic indices derived from 1 m and 5 m NEXTMap digital elevation models (DEMs), (iii) modelling hydrological disconnectivity from microtopography (HSA Index) and reinfiltration (SCIMAP), (iv) improving the national ditch and stream channel network used by the model by DEM extraction, and (v) using SCIMAP to improve predictions of erosion risk. The improved national source loading maps included mean nationally weighted farm-gate N and P imports (fertilizer, feed and livestock) and balance surpluses (kg/ha) calculated for each stocking rate and soil group (land use potential) category within each sector type (dairy, mixed livestock, suckler cattle, non-suckler cattle, sheep and tillage), using annual Teagasc National Farm Survey data (2008-15). Furthermore, updated national maps of soil P and atmospheric N and P deposition inputs were also used within the national source loading maps to improve model performance. National CSA maps for N and P for each pathway were then produced and evaluated using water quality monitoring data and field observations from the Environmental Protection Agency and Teagasc Agricultural Catchments Programme. These maps will be able to support sustainable intensification by informing farm and catchment management decisions such as where to cost effectively target mitigation measures to reduce environmental losses, where to distribute nutrient surpluses (to non-CSAs in nutrient deficit), and improving functional land management. Environmental Protection Agency Check for published version during checkdate report - AC

  • Open Access English
    Authors: 
    Bampoulas, Adamantio; Saffari, Mohhamad; Pallonetto, Fabiano; Mangina, Eleni; Finn, Donal;
    Publisher: IEEE
    Country: Ireland

    The 2019 IEEE 5th World Forum on Internet of Things (WF-IoT), Limerick, Ireland, 15-18 April 2019 This paper provides a research plan focusing on the application of self-learning techniques for energy systems integration in the residential building sector. Demand response is becoming increasingly important in the evolution of the power grid since demand no longer necessarily determines system supply but is now more closely constrained by generation profiles. Demand response can offer energy flexibility services across wholesale and balancing markets. Different applications have focused on the Internet of Things in demand response to assist customers, aggregators and utility companies to manage the energy consumption and energy usage through the adjustment of consumer behaviour. Even though there is extensive work in the literature regarding the potential of the commercial and the residential building sectors to provide flexibility, to date there is no standardised framework to evaluate this flexibility in a customer-Tailored way. At the same time, demand response events may affect occupant comfort expectations hindering the utilisation of flexibility that building energy systems can provide. In this research, the integration of machine learning algorithms into building control systems is investigated, in order to unify the monitoring and control of the separate systems under a holistic approach. This will allow the operation of the systems to be optimised with respect to reducing their energy consumption and their environmental footprint in tandem with the maximisation of flexibility, while maintaining occupant comfort. Science Foundation Ireland

Send a message
How can we help?
We usually respond in a few hours.