RESEARCH

As our planet warms, human societies, especially in developing countries, depend on our ability to maintain our food resources safe from climatic or climate-driven biological hazards. Such hazards can lead to a severe loss of plants and, in turn, to economic and even humanitarian disasters.

Here, we will develop tools that can:

1. Provide thermal maps that can be used to predict the locations of thermal extremes and of insect pests based on commonly available meteorological data; and
2. Use camera-trap data to identify the presence of pests in crops.

These AI modeling tools will enhance our ability to predict climate change effects on crops and their pests well beyond the current knowledge.

This work is also relevant to other human-related issues, such as the detection of disease vectors, as well as to climate change issues such as conservation and ecological studies that seek to predict the impacts of climate change on wildlife.

The figure shows a mosaic of microclimates in the Judean Desert. Red colors represent warm microclimates and blue colors colder ones

Extreme precipitation events are becoming more frequent and in areas where previously never existed. Accurate/prior prediction of light, medium and intense rain events is important on a time-scales of hours to allow adequate warnings and mitigation planning, especially in remote and developing countries. Indeed, such predictions are available (albeit not optimal yet) by numerical weather prediction (NWP) models or by ground-based radar systems.

However, NWP models are very costly in terms of processing time, memory, and expert-knowledge needs, while ground-based radars are not widespread enough, especially not in developing countries or in remote regions (e.g. desert areas or over the ocean). 

Here, we propose to utilize available near-real-time wide-coverage high temporal resolution geosynchronous satellite imagery and sparse precipitation data to construct a machine learning model for predicting rain intensity classes for short-term (0-6 hours) applications. We propose a tailor-made machine-learning architecture that combines both spatial (e.g. CNN) and time-series (ESN, LSTM) machine-learning approaches that will allow the ingestion and fusion of satellite-data on different times and spatial scales.

We are looking to apply our expertise in cloud detection and classification and retrieval approaches, with the support from the TAD center experts to derive a fast and simple yet useful enough rain predictor that can be used globally and can be easily embedded and implemented on a publicly available web-platform.