InfoSequia-4CAST aims to meet the needs of water management authorities and humanitarian-aid agencies by providing actionable, seasonal-scale outlooks of drought-induced crop yield and water supply failures, with the required level of accuracy, reliability, and location-specificity.
Water and food security are at risk in many places around the world, at present and even more so in the future, with significant economic and humanitarian consequences. Risk managers and decision-makers (e.g. water management authorities and humanitarian-aid agencies) can more effectively prevent harmful drought impacts if timely information is available on how the system is affected, and the probability of a system failure.
InfoSequia-4CAST combines historical and up-to-date observations of satellite-based meteorological and agricultural drought indices with climate variability indices, to generate seasonal outlooks of water supply and crop yield failure alerts. These impact-based indicators are computed using a simple, robust and easily understandable statistical forecasting-modelling framework. By making use of multi-sensor, state-of-the art satellite data fully integrated with predictive models, InfoSequia-4CAST provides locally-specific, 3-6 month outlooks and warnings of crop yield and water supply failures to end users through a simple, intuitive user interface.
The product is tailored to the needs of water managers who are looking to alleviate and mitigate impacts of forthcoming drought periods by taking strategic water management decisions, and humanitarian NGOs aiming to trigger ex-ante cash transfers with policyholders and farmer communities.
InfoSequia-4CAST focuses on the two aforementioned customer groups.
Water managers currently face too great a delay in detection of water demand-supply imbalances to trigger strategic actions. Humanitarian-aid agencies and NGOs lack actionable information on crop yield failures at the agricultural district level, which impedes them in determining the cost-effectiveness of cash transfer programmes and activating ex-ante payments. Both customer groups deal with a very weak local specificity and reliability of seasonal climate outlooks included in current Drought Early Warning Systems, which make use of complex dynamical forecasting models. Existing satellite-based drought monitoring systems, on the other hand, are location-specific but do not provide any information on expected conditions. Forecasts on the seasonal scale cannot be provided with sufficient accuracy by current numerical weather models.
The proposed development is incorporated into an existing toolbox for providing Drought and Early Warning Systems, called InfoSequia.
InfoSequia is a modular and flexible toolbox for the operational assessment of drought patterns and drought severity. Prior to the activity, the InfoSequia toolbox provided a comprehensive picture of historical and current drought status and impacts through its InfoSequia-MONITOR module, based mainly on Earth Observation data. The additional module InfoSequia-4CAST, is a major extension of current InfoSequia capabilities, responding to needs that have been identified in several previous applications.
InfoSequia-4CAST provides the user with timely, future outlooks of drought impacts on crop yield and water supply. These forecasts are provided on the seasonal scale (i.e. 3-6 months ahead). Seasonal outlooks are computed by a novel state-of-the-art Machine Learning technique. This technique has already been tested for applications related to crop production forecasting and agricultural drought risk financing.
The Fast-and-Frugal-Tree (FFT) algorithm uses predictor datasets (a range of climate variability indices alongside other climatic and vegetative indices) to generate FFTs predicting a binary outcome such as crop yields or water supply-demand balance above or below a given threshold (i.e. failure: yes/no). The activity includes collaboration with stakeholders in Spain, Colombia and Mozambique, in order to establish user requirements, inform system design, and achieve pilot implementation of the system in the second project year. Generic machine learning procedures for training the required FFTs are developed, and configured for these pilot areas. An intuitive user interface is developed for disseminating the output information to the end users. In addition to development of the forecasting functionality, InfoSequia-MONITOR is upgraded by integrating state-of-the art ESA satellite data and creating multi-sensor blended drought indices.
Key areas of innovation concern the integration of the following features:
Long-term solution with regular maintenance, technical support and upgrades.
The activity started in March 2021. Identification of key user requirements and conceptual system design were completed, and development and testing activities are underway towards a beta version in Q1 of 2022.”
+31 317 460050