REACT is Skytek's main commercial product, a SaaS platform that addresses the accumulation challenges of underwriting insurance risks.
REACT is a web-based system that uses real-time information to create accurate insights and actionable decision-ready data to support insurance and brokers in making smarter, faster, and better decisions. REACT provides the ability to integrate and analyse a variety of datasets, combining geolocation datasets (e.g. AIS), satellite imagery (optical and radar), big data, and machine learning, enabling monitoring of fixed and moving assets, including property, vessels and energy assets in real time, clearly identifying clusters, risks, and aggregated exposure.
REACT’s main features provide capabilities for:
- Global Risk Aggregation estimation, in a dynamic way and in real time, for any asset and in any location, with automated calculation of global exposure and ranking such as top 5 risk aggregation locations
- Aggregation can be analysed at portfolio or region level, with fully configurable threshold levels to suit the required outcome
- Severe Weather tool, allowing linkage with real time weather reports to monitor pre-event exposure aggregation and therefore support additional reinsurance purchase. Within this tool it is possible to analyse historical patterns of windstorm behaviours and locations affected
- Port Cargo accumulation information, allowing near real time cargo analysis, using Earth Observation imagery. We apply machine learning proprietary algorithms to count containers, refrigerated containers and cars at a port
- Automated and fully configurable alerts for monitored regions and assets
REACT is a powerful system that can be used to support:
- Modelling systems, as effectively complimentary tool
- Underwriting processes, for easy pre-screening of new clients, claims historical analysis, risk scoring and comparing
- Sanction compliance analysis and reporting, including War risk breach assessment
- ESG compliance and reporting, specifically in terms of environmental scores, sustainability and decent employment compliance
We plan to present how REACT has supported situations such as the
- Ever Given Grounded-Suez Canal, providing in real time the full list of assets in affected area, preventing loss creep and providing insurance with the ability to quickly report on potential exposure
- Several hurricane pre/post analysis examples, using Earth Observations data for damage assessment and providing insurances with an accurate and fast was to detect and view damage to individual properties within a portfolio, highlighting the storm path and providing supporting information on infrastructure damage.

Disaster Risk Financing (DRF) represents an effective risk management option, able to complement more traditional Disaster Risk Reduction measures by offering a lean way to unlock resources for a fast and prompt reaction when a disaster occurs. This is particularly important when sovereign risk is considered in countries where the magnitude of flood events often overcomes the response capacity of the institutions. A typical example is South East Asia where extensive monsoon flooding often endures for months and hits large geographical areas.
In this context, recent improvements in EO Products allowed the development of enhanced detection capacity in support of such applications. One example are the services developed by the project e-Drift (Disaster RIsk Financing and Transfer), financed by ESA and led by CIMA Research Foundation (IT).
The project is framed in the cooperation between ESA and the World Bank/DRF Initiative that provided not only guidance for the service development, but also created the preconditions for its operational use in the context of SEADRIF : a regional platform that provides participating nations in Southeast Asia with advisory and financial services to increase preparedness, resilience and cooperation in response to climate and disaster risks.
eDrift created a processing environment that enables access to seamless EO added value services in support of DRF applications.
In particular, the platform allows the continuous monitoring of an extended Region of Interest (e.g. a full country) taking advantage of the Sentinel-1 constellation global acquisition capability and of the free and long-term access to data guaranteed by the EU Copernicus services. A flood extent map can be updated every day by making use of any Sentinel-1 acquisition that intersects the region of interest, guaranteeing the best possible coverage. The process is fully automated and guarantees a high rate of data fetching.
Thanks to its reliability and high degree of automation the service does not require supervised intervention. Therefore, the same service can also be used to create an exhaustive set of past flood events on the analyzed area by processing the full archive of acquired satellite images. Such a product can be translated into historical flood frequency maps that are used to calibrate catastrophe models in support of insurance applications.
A first application that has been tested is parametric insurance to unlock resources for immediate and effective response in the aftermath of a flood event.
The eDrift services are fed into a platform supporting SEADRIF in the delivery of a parametric insurance product.
In this platform the EO services provided by eDrift are combined with flood models to determine the number of affected people at country level. This output can be used to activate a parametric insurance in support of the countries for response operations.
This service has been operational since February 2021. The EO component of the service is provided by the eDrift and the EO flood mapping is the first operational service on the market from the eDrift service portfolio.
Within the same period the eDrift project has been working to address challenges evidenced by the users especially in urban areas where the flood detection capabilities of synthetic aperture radar (SAR) sensors remains limited. Cutting edge algorithms for urban flood detection have been tested in several case studies and their operational use will soon be tested to enhance these types of services in support of DRF.

Soil Moisture Index Insurance Mozambique - protecting smallholder farmers against drought.

The right soil moisture conditions are essential to obtain good yield for farmers around the world, especially to those who farm in rainfed conditions. In Mozambique, agriculture provides livelihoods to almost 81 percent of the population (World Bank, 2015). The majority of crop production is undertaken by smallholder families who grow staple crops for consumption. These farming families face an increased likelihood of extreme weather events such as flood, drought, and cyclones due to climate change. Currently, only 34,378 of smallholder farmers in Mozambique have at least insurance against extreme climatic risks (MADER, 2021). This represents less than 1% of the total population of more than 4 million smallholder farmers in the country, as per the estimations contained in the most recent survey of the Ministry of Agriculture (FSDMoç, 2021).

Hollard Insurance is a pioneering insurance company attempting to de-risk Mozambican smallholder farmers by developing and delivering agricultural insurance products. In collaboration with Phoenix Seeds and a number of development agencies and national agricultural development projects, Hollard insurance provides farmers with improved crop seed varieties, bundled with satellite-based index insurance. Mozambican farmers who secure their inputs from the covered entities also receive reassurance that should a drought event occur, current and future growing seasons will not be a complete loss. Developing trust in the product among agrarian communities with low levels of insurance awareness is crucial for Hollard Insurance. They need to rely on a parametric insurance product which covers the actual crop damage on the ground, and is affordable and easy to explain to farmers.

The insurance product which covers farmers in the current growing season (nov ‘21 - april ‘22) is developed by reinsurance firm SwissRe using satellite-derived soil moisture data provided by VanderSat. The soil moisture measurements are based on passive microwave observations, which due to their unique sensor characteristics allow for all-weather retrievals and therefore do not have cloud cover issues as optical based EO data. VanderSat developed a unique patented technology (EU Patent # 17 728 899.0) that allows downscaling brightness temperatures to field level scale (100m), which are then transformed to soil moisture using the Land Parameter Retrieval Model (Owe et al., 2008; Van der Schalie et al., 2017). This is a large step forward from other state-of-the-art soil moisture data sets (e.g. Dorigo et al., 2017; Chan et al., 2018), which have a resolution of 9km at best. Soil moisture indices reflect directly the water content in the soil which is available for the plant to grow, and therefore correlate highly with obtained crop yields in dominantly rainfed farming conditions compared to vegetation and weather-derived indices (Mladenova et al. , 2017; Vergopolan et al., 2021). Soil Moisture data at field level with a long historical record (20 years, by using AMSR-E, AMSR2 and SMAP) enables the development of scalable index-based insurance products.

The drought insurance product covers the seeding, vegetative and harvesting phases of plant growth and is tuned to the drought sensitivities of the insured crop. For each growing phase, different drought triggers are developed using parametric rating (SwissRe, 2021). The satellite tracks developing drought conditions during the season, and a payout is triggered when a drought becomes severe. The soil moisture values and payouts can be accessed through an online dashboard which improves transparency in the insurance value chain. Drought is the most important peril that inland farmers are facing in Mozambique. Farmers in the coastal regions are frequently plagued with tropical cyclones that wipe out harvests. Ongoing research and development activities are performed to best capture the impact of cyclones on coastal agricultural land using parametric index insurance.

References

World Bank (2015), Mozambique: Agricultural Sector Risk Assessment. Risk Prioritization, accessible via: https://openknowledge.worldbank.org/handle/10986/22748

Ministério da Agricultura e Desenvolvimento Rural (MADER) (2021), Inquérito Agrário Integrado 2020, Maputo – MADER, accessible via: https://www.agricultura.gov.mz/wp-content/uploads/2021/06/MADER_Inquerito_Agrario_2020.pdf

Financial Sector Deepening Mozambique (FSDMoç) (2021), Mozambique Inclusive Insurance Landscape Report 2021, accessible via:
http://fsdmoc.com/news/launching-report-landscape-inclusive-insurance-mozambique/

Owe, M., de Jeu, R., & Holmes, T. (2008). Multisensor historical climatology of satellite‐derived global land surface moisture. Journal of Geophysical Research: Earth Surface, 113(F1).

Van der Schalie, R., de Jeu, R. A., Kerr, Y. H., Wigneron, J. P., Rodríguez-Fernández, N. J., Al-Yaari, A., ... & Drusch, M. (2017). The merging of radiative transfer based surface soil moisture data from SMOS and AMSR-E. Remote Sensing of Environment, 189, 180-193.

Dorigo, W., Wagner, W., Albergel, C., Albrecht, F., Balsamo, G., Brocca, L., ... & Lecomte, P. (2017). ESA CCI Soil Moisture for improved Earth system understanding: State-of-the art and future directions. Remote Sensing of Environment, 203, 185-215.

Chan, S. K., Bindlish, R., O'Neill, P., Jackson, T., Njoku, E., Dunbar, S., ... & Kerr, Y. (2018). Development and assessment of the SMAP enhanced passive soil moisture product. Remote sensing of environment, 204, 931-941.

Mladenova, I. E., Bolten, J. D., Crow, W. T., Anderson, M. C., Hain, C. R., Johnson, D. M., & Mueller, R. (2017). Intercomparison of soil moisture, evaporative stress, and vegetation indices for estimating corn and soybean yields over the US. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(4), 1328-1343.

Vergopolan, N., Xiong, S., Estes, L., Wanders, N., Chaney, N. W., Wood, E. F., ... & Sheffield, J. (2021). Field-scale soil moisture bridges the spatial-scale gap between drought monitoring and agricultural yields. Hydrology and Earth System Sciences, 25(4), 1827-1847.

SwissRe (2021), Drought is insurable, accessible via: https://www.swissre.com/risk-knowledge/mitigating-climate-risk/natcat-2019/drought-is-insurable.html

Many parametric or index-based drought risk financing instruments are based on satellite-derived rainfall, temperature and/or vegetation health data. However, an underlying issue is that indices often do not perfectly correlate to the actual losses experienced by the policy holders. The resulting increased basis risk can diminish demand for parametric drought risk insurance. Remotely sensed soil moisture (SM) can help decrease basis risk in parametric drought insurance through 1) complementary and/or improved parameters and variables used in existing models such as the Water Requirement Satisfaction Index (WRSI), 2) shadow-models to cross-check, test or validate payouts triggered through other indicators and models or 3) potentially through development of a stand-alone product. Here, we will demonstrate the use of a combined Sentinel-1 and Metop ASCAT high resolution soil moisture dataset to predict yield and develop an early-warning yield deficiency indicator for Senegal.

Soil moisture is retrieved from the Advanced SCATterometers (ASCAT) on-board the Metop satellite series, which has an original spatial sampling of 12.5 km. Sentinel-1 backscatter data at 500 m spatial sampling is used to downscale the Metop ASCAT surface soil moisture data to 500 m. The underlying concept is the temporal stability of surface soil moisture: In the temporal domain surface soil moisture measured at specific locations is correlated to the surface soil moisture content of neighbouring areas, where neighbours with similar physical properties (like soil texture, land cover and terrain) show a higher coherence to the local surface soil moisture than others. In addition to soil moisture, freely available rainfall from Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS) and Copernicus Global Land Service NDVI were used. All datasets were spatially resampled to a 500 m grid, temporally aggregated to monthly anomalies and finally detrended and standardized. Data on yields was obtained from the Food and Agriculture Organization of the United Nations (FAO). Data on crop growth areas is based on FAO Global Agro-Ecological Zones (GAEZ) information and Livelihood zones (2015).

First, regression analysis with yearly yield data was performed per EO dataset for single months. The EO datasets were aggregated over areas where the specific crop was grown. Secondly, based on these results multiple linear regression was performed using the months and variables with the highest explanatory power. The multiple linear regression was used to provide spatially varying yield predictions by trading time for space. The spatial predictions were validated using sub-national yield data from Senegal and reports from the African Risk Capacity (ARC).

The analysis demonstrates the added-value of satellite soil moisture for early yield prediction. Soil moisture showed a high predictive skill early in the growing season: negative early season soil moisture anomalies often lead to lower yields. NDVI showed more predictive power later in the growing season. Combining anomalies of the optimal months based on the different variables in multiple linear regression improved yield prediction. Especially at the start of the season soil moisture improves predictions, with the ability to explain 60% (groundnut), 63% (millet), 76% (sorghum) and 67% (maize) of yield variability. These findings are particularly relevant for parametric drought insurance, because an earlier detection of drought conditions enables earlier payouts, which then help to mitigate the development of shocks into serious crises with often long-lasting socioeconomic effects.

Based on the analysis a yield deficiency indicator can be developed, which can provide spatial information on yield deficiencies. Yield deficiencies were compared to sub-national yield information and WRSI information as reported by the African Risk Capacity end of season reports. Strong spatial correspondence was found between the yield deficiency indicator and WRSI. For example, for millet in Senegal for the drought 2019 strong yield deficiencies in the provinces of Ziguinchor, Fattick, Kaolack and Kaffrine and moderate deficiencies in Thies, Louga and Tambacounda were found. This corresponded to low WRSI as reported by the African Risk Capacity in its end of season report of 2019. The analysis shows very clearly that soil moisture can be a valuable tool for anticipatory drought risk financing and early warning systems.

This analysis was performed in collaboration with the World Bank Disaster Risk and Financing Program and Global Risk Financing Facility.

The economic impacts of floods push people into poverty and cause setbacks to development as government budgets are stretched and people without financial protection are forced to sell assets. Investments in flood mitigation and adaptation, such as expanding insurance coverage through index based insurance, i.e. direct payouts based on predetermined indexes of e.g. flooded area, could reduce anticipated losses from floods and increase resilience. Insurance penetration remains low ( < 1%) for climate-vulnerable populations in countries like Bangladesh, which urgently need financial protection from extreme floods to protect development. Expanding insurance coverage requires the ability to quantify flood risk and monitor it in near real-time in remote locations, which is challenging due to limited data in most areas. Satellite observations have the potential to fill this data gap and expand insurance coverage by providing globally available observations available at regular intervals.

Algorithms to map flood extent are improving by leveraging machine learning and multiple sensors. One way to estimate the frequency of extreme floods is to measure the spatial extent of inundation directly from space. Given the growing length of the satellite record, time series of inundated area could be used for exceedance probability estimation to develop insurance products, but relies on the availability of the data over extended periods of time ( > 30 years).

High spatial resolution satellites (such as Sentinel-1 and 2, 10m) have not been around long enough for reliable exceedance probability estimates to design index insurance triggers.Using deep learning, we fuse the daily MODIS time series with Sentinel-1 and Harmonised Landsat Sentinel-2 (HLS) data to create 20 year historical inundated area estimates over Bangladesh.
We benchmark consistency of the time series against in situ records of 42 water level stations for validation. Satellite fusion could generate longer time series of inundation, to eventually generate return period estimates at watershed or country scale beyond Bangladesh.

Agricultural production inherits comparably high production risks and weather-related crop yield losses are even expected to increase due to climate change. The government of India is supporting risk mitigation of Indian farmers for crop loss caused by natural disasters through the Pradhan Mantri Fasal Bima Yojana (PMFBY) launched in 2016. PMFBY aims to support sustainable production in the agricultural sector. PMFBY supersedes the earlier insurance schemes National Agriculture Insurance Scheme (NAIS), Weather-based Crop Insurance scheme and Modified National Agricultural Insurance Scheme (MNAIS). The crop insurance coverage under PMFBY increased substantially since its inception, reaching up to 50% (in 2018-19), with a governmental contribution in the fiscal year 2021-22 of approx. 1.8 billion EUR. PMFBY requires the enhanced usage of technology for the reporting to the National Crop Insurance Program (NCIP) Portal and encourages the move towards increasing use of remote sensing and Artificial Intelligence/ Machine Learning methods.
The overall aim of the India Crop Monitoring Project, a cooperation between Munich Re, Potsdam Institute for Climate Impact Research (PIK) and GAF AG, is to support direct agro-insurers in India with information about historical and current state of agricultural land through a combination of Earth Observation and weather information products. This information is retrievable via the web application AgroView®.
AgroView® is a single-page web GIS application, using a frontend based on HTML5, JavaScript and CSS technologies. The backend contains a spring framework with REST services, Java and Tomcat; PostgreSQL/ PostGIS are employed as a database. OGC-compliant geodata services, such as WMS, are provided via GeoServer. The whole application and its components are implemented in a Kubernetes Cluster in the Open Telekom Cloud (OTC) environment, offering a scalable, high-performance processing environment, with direct access to various Earth Observation Data Archives.
AgroView® integrates, manages and displays geographical raster, vector and alphanumerical information from various sources. Besides integration of data from external sources (e.g. administrative boundaries, weather data, historic events), historic and current satellite data is integrated and analysed (e.g. Sentinel-1 and Sentinel-2, CHIRPS, MODIS). The data backend of the applications gathers satellite images and weather data from the providers’ archives, processes them into relevant crop health and weather condition/ drought indicators in a fully automated processing chain, and provides the produced information products to the User in near-real time. The analysis functionality of the application allows the exploitation of the multitude of data at different scales from national to field level, and throughout time at full temporal resolution of the source data from historic to current.
With its wide range of functionality, AgroView® supports the User across the full Crop Insurance Cycle, and its key features all the User to reduce risks throughout the different phases of the growing season efficiently, and increase profitability. In the insurance tendering phase, the User can analyse historic weather patterns and agricultural variations for risk analysis and pricing. Real-time and historical crop field information helps to understand land use in support of decision of enrolment areas in support of insurance coverage and expansion. During the sowing period, the User can monitor rainfall and soil moisture to derive probability of crop failure, and help to invoke prevented sowing and the assessment of correspondent triggers.
Throughout the growing season, AgroView® provides crop health monitoring through a set of vegetation indices, and the User is alerted when crop condition indicates agricultural drought. The continuous monitoring of weather data allows the timely detection of mid-season adversities such as floods, prolonged dry spells or severe droughts.
In addition to this continuous monitoring of vegetation and rainfall conditions through the application, the User provided with fortnightly reports on his portfolio areas in PDF format through the fully automated reporting function of AgroView®. This automated reporting allows the User to make informed decisions in a timely and efficient manner.
During harvest period, the application supports post-harvest loss assessments by combining the monitoring of harvesting patterns through vegetation indices in combination with real time rainfall data tracking and identification of peak rainfall periods. With its integrated Yield Estimation System (YES), the User benefits from predictive crop yield modelling through the DSSAT model. Finally, the User can plan his crop cutting experiments for yield assessment based on the predicted yields for major crops and NDVI data, for reporting into the PMFBY system.
In summary, the stakeholders benefit from full adaptability to their specific business requirements in the insurance sector, and fast integration of dedicated geo-technological data analytics fully scalable from national to field level. The application provides the agro-insurance User a wide range of built-in tools and functionalities, adjusted to his needs in the PMFBY system, in a User-friendly package through easy browser access. It therefore constitutes a fully-fledged, tailored digital farming solution for insurance in India.