Indigenous Knowledge Aware Drought Monitoring, Forecasting and - - PowerPoint PPT Presentation

indigenous knowledge aware
SMART_READER_LITE
LIVE PREVIEW

Indigenous Knowledge Aware Drought Monitoring, Forecasting and - - PowerPoint PPT Presentation

Indigenous Knowledge Aware Drought Monitoring, Forecasting and Prediction using Deep Learning Techniques Kidane W. Degefa kidane1982@gmail.com [or] kidane.woldemariyam@haramaya.edu.et Lecturer and Researcher at Haramaya Univeristy (Ethiopia)


slide-1
SLIDE 1

Indigenous Knowledge Aware Drought Monitoring, Forecasting and Prediction using Deep Learning Techniques

Kidane W. Degefa kidane1982@gmail.com [or] kidane.woldemariyam@haramaya.edu.et Lecturer and Researcher at Haramaya Univeristy (Ethiopia) April, 2020

slide-2
SLIDE 2

Drought is a natural environmental hazard causing adverse impacts on vegetation, animals, and people.

  • 1. COMMUNITY ORIENTED SOLUTION (INDIGENOUS KNOWLEDGE)
  • 2. TECHNOLOGICALLY ASSISTED SOLUTION (AI / DEEP LEARNING)

2

slide-3
SLIDE 3

Statement of the Problem

 Community Oriented Solution

 Certainty  Structured Representation

 Technologically Assisted Solution

 Large data set requirement  Model Interpretability & Visualization

THE NATURAL PROGRESSION: STRUCTURED INDIGENOUS KNOWLEDGE BASED LEARNING

3

slide-4
SLIDE 4

The general objective of this proposed research work is to design hybrid comprehensive framework for drought monitoring, forecasting and prediction using scientific and indigenous knowledge.

KNOWLEDGE ORIENTED EXPLAINABLE- MODEL

4

slide-5
SLIDE 5

Comprehensive Architecture

5

Embedding Oriented Deep Learning Aggregation with Knowledge Graph

Different types of data sources for drought modelling Indigenous Knowledge aware Drought Monitoring, Forecasting and Prediction Models

Knowledge Graph based Deep Learning Inputs Outputs Drought Indigenous Knowledge Graph(Ontology)

Visualization (Experts) Knowledge Graph based Explanation (Non-Experts)

Visualization/Explanation

slide-6
SLIDE 6

What is new?

 Learning from reasonable dataset  Participatory Technological Solution  Indigenous knowledge modelling and preservation  AI model performance improvement and explainability  Disambiguating and recognizing entities in context of drought

6

slide-7
SLIDE 7

Conclusion

Deep Learning(connectionist AI) + Indigenous KGs(symbolic AI) = (Comprehensive, Explainable and Adaptable AI) [for Drought Monitoring, Forecasting and Prediction]

7

slide-8
SLIDE 8

Thank You for Your Attention!!!

Today’s effective drought monitoring is Tomorrow’s life saver!

8