2021-10-28, 14:45–15:30, RoomC
Artificial Intelligence (AI) is a powerful science that utilizes sufficient
methodologies, strategies, and systems to take care of unsolvable real-world issues.
There is a wide range of technological advancements and research is going on to
solve many real-time problems with regards to all different aspects of today’s society.
Recent years have witnessed significant advances in geospatial artificial intelligence
(GeoAI), which is the integration of geospatial studies and AI, especially machine
learning and deep learning methods and the latest AI technologies in both academia
and industry. Setting up AI-based machines in solving geospatial applications
requires a high amount of computing. With processors like IBM POWER9, we can
address complex workloads with a huge amount of data while data visualization,
statistical analysis, pattern recognition, and inference building in a very fast and
efficient manner. Thus combining H2O driverless AI and IBM power systems for
enabling geospatial applications to harness AI for competitive gain.
Keywords: GeoAI, IBM POWER9, H2O.ai
Proposed System: As there is a large amount of satellite imagery captured from
various satellites available today, we can able to build AI models for the purpose of
solving many problems in the domains like agriculture, disaster management, urban
planning, etc But these applications need processors that are well equipped to
handle millions of workloads in order to develop the models with millions of satellite
imagery., It also requires a large amount of time and manpower to recognize
patterns from those images to extract insightful information like exo-planet detection,
predicting anomalies in the signals. So, using driverless AI on IBM Power Systems to
accelerate machine learning insights by up to 5X on IBM POWER9 processor-based
power systems. In the H2O.ai platform, Driverless AI automates some of the most
difficult data science and machine learning workflows such as feature engineering,
model validation, model tuning, model selection, and model deployment with no code
environment. It also delivers automatic machine learning interpretability, time-series,
natural language processing with pytorch and tensorflow, image processing with
tensorflow and automatic pipeline generation for model scoring. Thus, by using
automation and state-of-the-art computing power to accomplish tasks that can take
humans months in just minutes or hours. The H2O.ai open-source platform works
with R, Python, Scala on Hadoop/Yarn, and Spark. It includes multi-GPU algorithms
for XGBoost, GLM, K-Means, and more. It was also specifically designed to take advantage of graphical processing units (GPUs), including multi-GPU workstations
and servers such as IBM’s POWER9.
Expected contributions: The geospatial applications can be run efficiently on IBM
POWER9 using H2O.ai. Driverless AI. The proposed system will be a better
approach as the platform is optimized to take advantage of GPU acceleration to
achieve up to 40X speedups for automatic machine learning and gives significant
speedups for use cases involving images.
1. Poverty prediction by satellite imagery: By using night light satellite
imagery predicting the wealth of the region based on luminosity from the
intensity of the pixel.
2. Urban planning: With attribute information from the geospatial images over a
period of time to create and visualize various planning scenarios for decision
Bagavathy Priya is a data analyst at ShopUp, a startup company
based in Bangladesh. Bagavathy is passionate about Artificial Intelligence and
familiar with machine learning, deep learning, and other statistical concepts. She is
proficient in python, SQL, and BigQuery and currently working on ML use cases
using IBM's POWER9 server.