14
PUBLIC SAP Esri Spatial Hackathon GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February 6, 2018

SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

  • Upload
    lyxuyen

  • View
    222

  • Download
    1

Embed Size (px)

Citation preview

Page 1: SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

PUBLIC

SAP Esri Spatial Hackathon – GeoML

Palm Springs, California, March 3rd - 5th, 2018

Hinnerk Gildhoff / February 6, 2018

Page 2: SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

2PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ

Disclaimer

This presentation outlines our general product direction and should not be relied on in making a

purchase decision. This presentation is not subject to your license agreement or any other agreement

with SAP. SAP has no obligation to pursue any course of business outlined in this presentation or to

develop or release any functionality mentioned in this presentation. This presentation and SAP's

strategy and possible future developments are subject to change and may be changed by SAP at any

time for any reason without notice. This document is provided without a warranty of any kind, either

express or implied, including but not limited to, the implied warranties of merchantability, fitness for a

particular purpose, or non-infringement. SAP assumes no responsibility for errors or omissions in this

document, except if such damages were caused by SAP intentionally or grossly negligent.

Page 3: SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

3PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ

Agenda

• AFL & PAL (ML)

• EML & TensorFlow (DL)

• Demo

Page 4: SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

4PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ

Database management

Web server JavaScript

Graphic modeler

Data virtualizationExtract, load, transform

and replication

Columnar store –Transaction and

analytical processing

Multicore and parallelization

Advanced compression

Multitenancy Multitier storage

Graph Predictive Search

Seriesdata

Business functions

Apache Hadoop and Apache Spark integration

Streaming analytics

Application lifecycle management

High availability anddisaster recovery

OpennessDatamodeling

Administration and security

Spatial

Text analytics

SAP Fiori® user experience(UX)

Application development Data integration and qualityAdvanced analytical processing

SAP HANA Architecture

SAP HANA® PlatformOn premise | Cloud

Dataquality

Remote data sync

SAP, ISV and Custom Applications

All Devices

OLTP + OLAP ONE Open Platform ONE Copy of the Data

Page 5: SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

5PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ

The SAP HANA Predictive Analysis Library (PAL)

SAP HANA embeds multiple advanced analytics function libraries, designed

and optimized for massive parallel in-memory processing of predictive

algorithms on largest multi-core and terabyte-scale memory hardware

platforms

Predictive Analysis Library

The SAP HANA core of numerous powerful, native predictive algorithms for

in-database & in-memory processing that fully exploit the power and speed

of SAP HANA, resulting in quicker insight and faster implementations.

Content and Usage

The library includes common as well as specialized algorithms targeting various data mining and machine learning areas

Leveraged and embedded in native SAP applications and usage from within SAP HANA development tools as well as SAP Predictive Analytics.

Scenarios & Use Cases

Various LoB / industry scenarios making use of Association Analysis, Time Series Forecasting, Link Prediction, Predictive Modeling, etc.

SAP HANA Platform

Page 6: SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

6PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ

SAP HANA Predictive Analysis LibraryRoadmap - New and enhanced Algorithms in SAP HANA 2 SPS0

▪Classification Analysis▪ CART

▪ C4.5 Decision Tree Analysis

▪ CHAID Decision Tree Analysis

▪ K Nearest Neighbour

▪ Logistic Regression Elastic Net

▪ Back-Propagation (Neural Network)

▪ Naïve Bayes

▪ Support Vector Machine

▪ Random Forests

▪ Gradient Boosting Decision Tree

(GBDT)

▪ Linear Discriminant Analysis (LDA)

▪ Confusion Matrix

▪ Area Under Curve (AUC)

▪ Parameter Selection / Model Evaluation

▪Regression▪ Multiple Linear Regression Elastic Net

▪ Polynomial, Exponential, Bi-Variate

Geometric, Bi-Variate Logarithmic

Regression

▪ Generalized Linear Model (GLM)

▪ Cox Proportional Hazards Model

▪Association Analysis▪ Apriori

▪ Apriori Lite

▪ FP-Growth

▪ KORD – Top K Rule Discovery

▪ Sequential Pattern Mining

▪Probability Distribution▪ Distribution Fit/ Weibull analysis

▪ Cumulative Distribution Function

▪ Quantile Function

▪ Kaplan-Meier Survival Analysis

▪Outlier Detection▪ Inter-Quartile Range Test (Tukey’s

Test)

▪ Variance Test

▪ Anomaly Detection

▪ Grubbs Outlier Test

▪ Link Prediction▪ Common Neighbors

▪ Jaccard’s Coefficient

▪ Adamic/Adar

▪ Katzβ

▪Statistic Functions ▪ Mean, Median, Variance, Standard

Deviation, Kurtosis, Skewness

▪ Covariance Matrix

▪ Pearson Correlations Matrix

▪ Chi-squared Tests:

- Test of Quality of Fit

- Test of Independence

▪ F-test (variance equal test)

▪ Data Summary

▪ Data Preparation

▪ Sampling

▪ Binning

▪ Scaling

▪ Partitioning

▪ Principal Component Analysis

(PCA) / PCA Projection

▪Other▪ Weighted Scores Table

▪ Substitute Missing Values

▪Cluster Analysis▪ ABC Classification

▪ DBSCAN

▪ K-Means

▪ K-Medoid Clustering

▪ K-Medians

▪ Kohonen Self Organized Maps

▪ Agglomerate Hierarchical

▪ Affinity Propagation

▪ Latent Dirichlet Allocation (LDA)

▪ Gaussian Mixture Model (GMM)

▪ Cluster Assignment

▪ Time Series Analysis▪ Single/Double/ Brown /Triple Exp.Smoothing

▪ Forecast Smoothing

▪ Auto - ARIMA/ Seasonal ARIMA

▪ Croston Method

▪ Forecast Accuracy Measure

▪ Linear Regression with Damped Trend and

Seasonal Adjust

▪ Test for White Noise, Trend, Seasonality

▪ Fast Fourier Transform (FFT)

▪ Correlation Function

Page 7: SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

7PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ

RecommendationSocial SDK/APIConnectors

SAP RDS SAP Data Science

Predictive Analysis

Library

Automated

Predictive LibraryR-Scripts

In-Memory Processing Engine25+ Industries 11+ LoBs

O&G,

Manufacturin

g

& Utilities

Public Sector

& Healthcare

Financial

&

Insurance

Services

TelecommunicationsRetail &

Consumer

Products

Predictive ApplicationsSAP HANA Third Party Data Sources

Relational

DatabasesBig Data

Sources

CRM/ERP

Data

Sources

Custom

Data

Sources

Any Data Source in the world

Text Analytics Spatial Analytics Graph

On-Premise, Cloud & Hybrid

DATA

PREP

MODELER REPORTS

& VIZ

SCORING MODEL

MANAGER

Advanced Analytics Solution from SAPDeveloping fast predictive models that deliver fast results

Page 8: SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

8PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ

Geo-MLExtracting Business Information

Classification

(land cover, land usage, object, …)Risk Prediction & Anomaly Detection

(wildfire, landslide, drought, flood, crop disease, …)

Page 9: SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

9PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ

Landslide Risk PredictionModel Inputs

Vegetation Changes

NDVI time series, Forest loss

Weather forecasts

Heavy rainfall as trigger for landslides

Digital Elevation Model

Elevation, Aspect, Slope

Lithology

Physical & geochemical properties of ground

material

Terrain Displacement

Earthquakes as trigger for landslides

Detection of slow landslides

Infrastructure

Distance to roads and drainage

Page 10: SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

10PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ

Landslide Risk PredictionModel inference

Prediction system based on

• Radar and optical EO data with gridded data

• Supervised deep learning (CNN, LSTM)

Application

• SAP Cloud Platform service

• SAP HANA advanced analytics (spatial & graph)

• Combination of EO-, open- and weather-data

Save lives and optimize rescue management

• Risk forecast for the next ten days

• Detailed emergency reports

• Improved decision making (emergency call)

• Reduce risk for humanitarian disaster

Page 11: SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

11PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ

SAP HANA Extended Machine Learning Library (EML)Deep Learning

SELECT * FROM POI

WHERE location.ST_Intersects (

landslide_risk(‘EU‘, 0.9) );

Integration of Google TensorFlow with

SAP HANA is based on

• SAP HANA Application Function

Library (AFL)

• Google’s gRPC remote procedure call

package

• Separate server process that hosts the

actual machine learning functionality

Page 12: SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

12PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ

SAP HANA

ODBC

ArcGIS

Enterprise

SAP Business-

Objects CloudArcGIS Portal

ArcGIS Pro /

Desktop

Query

Layer

ODBC

SAPUI5 Esri App

on XSA

Extended Application

Services

SAP HANA SpatialEsri Applications

Map Service,

Feature Service csv, shapefile

upload

Page 13: SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

13PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ

Software & LicenseHow to get started

SAP HANA Application Function Library (AFL)

SAP HANA Predictive Analysis Library (PAL)

https://help.sap.com/viewer/2cfbc5cf2bc14f028cfbe2a2bba60a50/2.0.01/en-US

SAP HANA Extended Machine Learning Library (EML)

https://help.sap.com/viewer/ab6b04eb12d3452aa904d5823416a065/2.0.02/en-US/abfc6b11fc3e41e98408df593a06ad16.html

Page 14: SAP Esri Spatial Hackathon GeoML - · PDF file06/02/2018 · PUBLIC SAP Esri Spatial Hackathon –GeoML Palm Springs, California, March 3rd - 5th, 2018 Hinnerk Gildhoff / February

14PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ

Happy Mapping!

SAP HANA Spatial Reference

Earth Observation Service

Thank You !

[email protected]

@HinnerkGildhoff

SAP HANA Academy

SAP HANA & Esri

#SAPEsri

#DevSummit

#SAPHANA

#ESRI