Erkin Isaev

I am a data scientist within the Climate Change and Resilience team at the FAO UN regional office for Asia and the Pacific. I work on assisting rural communities, governments, and NGOs in adapting to and mitigating the causes and impacts of climate change by assessing physical climate risks. I focus on developing applied, interdisciplinary solutions by integrating weather/climate, loss/damage, and socioeconomic data in the field of disaster risk management, extreme weather/climate impact-based forecasting, and early warning/Anticipatory Actions that aim to actually accomplish what omnipresent buzzwords (resilience, machine learning, etc.) are promising. Main duties: - Developing GCF project proposals (climate rationale and theory of changes). -Lead the development, and validation of triggering methodologies of climate hazards (drought, flood, tropical cyclone etc.) for Anticipatory Action over Asian and Pacific countries; - Develop guidelines and tools on the selection of climate, livelihood and food security indicators and thresholds for anticipating climate impacts on agriculture and food security; -Work closely with government counterparts to explore how triggering methodologies can be integrated in pre-disaster actions and potential expansions to national level.

Conduct research on dynamical downscaling of a high-resolution (5 km) climate model over Central Asia using MRI regional climate model known as NHRCM by using ssp585.

I work on helping Central Asian governments and rural peoples adapt to the impacts of climate change. Applied machine learning (NLP), statistical analysis, numerical modeling (deterministic models) and qualitative methods in research on climate change, remote sensing, air pollution, weather forecast, crop and water assessment, DRR. - Data scientist with expert knowledge on machine learning, statistics, probabilistic modeling, data analysis, predictive analytics, modeling and advanced risk modeling - Experienced working cross-functionally with different stakeholders to define problem statements, collect data, build analytical models to make informed decisions and set smart business strategies.

Using Cloud Computing with AWS Amazon Web Services to run Numerical weather prediction over Central Asia

Develop presentations based on identified needs including the detailed curriculum, timeframe for capacity building of Turkmenhydromet staff and conduct trainings. - Advanced automated meteorological measuring information systems and weather radar stations (02/14/2022-02/18/2022) - Advanced meteorological measuring information systems and weather radar stations (03/24/2022-04/08/2022) - Advanced meteorological measuring information systems and agrometeorological equipment’s (08/02/2022-08/19/2022)

Develop presentations based on identified needs including the detailed curriculum, timeframe for capacity building of Turkmenhydromet staff; Based on the agreement and coordination with GSP and Turkmenhydromet and other stakeholders, conduct training for about 15 participants

Prepared and conducted trainings on statistical processing of climate data for the staff of the Department of Monitoring and Forecasting of the Ministry of Emergency Situations of the Kyrgyz Republic

Provide training for Agency on hydrometeorology staff on: - hydro and meteorological hazards monitoring, - hazards thresholds, warnings and alerts as a part of climate risk assessment for agriculture sectors, - use of GIS technologies, using ML technologies in meteorology, working with big data format( NetCDF, GRIB2, etc.) - Maintenance of the WRF-ARW hydrodynamic model for the sustainable preparation of the forecast of hazardous hydrometeorological and agrometeorological phenomena.

Professional, scientific and technical activities on discipline: - Physics, - GIS, - Theory probability and mathematical statistics, - Econometrics, - Numerical methods. Providing advisory support for students in improvement of study methods and development effective research directions.

A modified PBL parameterization scheme was proposed, implemented and tested. An improvement in the quality of the forecast of meteorological values is shown when using a modified parameterization scheme for PBL, especially in an area where the relief is exposed to the influence of large-scale flows. A package was developed and implemented in the form of a software module for the verification and assimilation of the hydrodynamic forecast of meteorological variables over area with complex orography. Implemented system of hydrodynamic modeling of atmospheric processes in the Kyrgyzhydromet increased the accuracy of weather forecasts and it also made possible to give more accurate forecasts in difficult mountainous regions.

▪ Shell program scripting in Linux ▪ Excellent programming skills, including Fortran90 / 95, Java, Pascal, Python ▪ Experience with tools for visualization (GIS), such as GRDAS, Grapher, Arcgis, QGIS ▪ Experience with hydrodynamic atmosphere model WRF - 10 years ▪ Knowledge of the dynamics and physics of the atmosphere, on numerical methods ▪ Advanced theoretical and practical knowledge of statistics concepts and methodologies, modeling and predictive analysis ▪ Experience in remote sensing interpretation and analysis, NDVI methodology. Knowledge in using data from satellites :Sentinel -1 and 2, metop(ascat) Thesis Title: Hydrodynamic modeling of atmospheric processes on “Kyrgyzstan)” [“Excellent”]. Successfully developed data analysis in the context of disaster risk, resilience and development. Improved experience for quantitative analysis of risk and application of GIS.