Operational monitoring and Forecasting system for Resilience of agriculture and forestry under intensification of the WAteR cycle: a Big Data approach

Id:
4

Funder:
JPI W2015

Co-Funder:
Centre for the development of Industrial Technology (CDTI) Flanders Innovation & Entrepreneurship (VLAIO) Innovation Fund Denmark (IFD)

Title:
Operational monitoring and Forecasting system for Resilience of agriculture and forestry under intensification of the WAteR cycle: a Big Data approach

Project Reference:
--

Acronym:
FORWARD

Coordinator:
Fernández Alberto

Organisation:
TSK

Country:
SPAIN

SRIA Themes:

Start Date:
01/06/2017

End Date:
30/05/2019

Website:
http://forward.grupotsk.com/

Summary:
The main objective of FORWARD is to understand and increase the resilience of water resources of agricultural systems and forestry through data mining and modelling in a Big Data setting. Hereto, the project has the following three specific objectives: 1. To develop and implement an extensible and tailorable Big Data approach and framework able to manage and process multivariable information sources (see the Methodology section for a short and preliminary list of sources and variables), data-mining techniques and models at several scales (local, regional, nation and continental). 2. To provide improved model forecasting (daily-monthly-seasonal-long term; and at different spatial scales) and monitoring capabilities of eco-hydrological variables and indicators (see the Methodology section for a preliminary list of indicators) relevant to forestry and agricultural applications by combining different modeling types (data-driven, process based and statistical time series analysis) in a Big Data framework 3. To understand the resilience of forest and agricultural ecosystems in water-limited regions to extreme events, in particular drought, and in the context of climate change. Provide maps of most vulnerable sites to those through combining all available data sources and advanced data mining techniques. To achieve these objectives, six specific challenges need to be tackled: (1) development of efficient data gathering protocols, including synchronization with (highly variable) data sets. Eco-hydrological data, in particular, is characterized by different spatial and temporal resolutions, gaps and unreliable data samples, necessitating proper processing protocols; (2) implementation of a scalable database warehouse; (3) configuration of industry standard APIs to ensure proper interfacing with other systems and models; (4) development and application of efficient and generalized data mining techniques (e.g. for anomaly detection); (5) development of (locally) enhanced process-based models through data-assimilation and integration with data-driven modelling; (6) integration of the development into the Big Data architecture and its application on the selected cases of study.

Keywords:
Resilience; Big Data; ecohydrology; Earth Observations

Partner 1:
Alberto Fernández Villán (TSK) - SPAIN

Partner 2:
Vincent Wolfs  (Sumaqua) - EU

Partner 3:
Mónica García  (Technical University of Denmark) - DENMARK