The ecology centre university of queensland australia Zonae Cogito - A decision support system for.

Slides:



Advertisements
Similar presentations
Intelligent Tools for Techno- Economic Modelling and Network Design Tim Glover Chris Voudouris Anthony Conway Edward Tsang Ali Rais Shaghaghi Michael Kampouridis.
Advertisements

Software Analysis Tools
Temi Avanzati di Intelligenza Artificiale - Intro1 Temi Avanzati di Intelligenza Artificiale Prof. Vincenzo Cutello Department of Mathematics and Computer.
Slides from: Doug Gray, David Poole
ArcLogistics Routing Software for Special Needs, Maintenance and Delivery.
1 The RobOff framework and software: analysis of alternative land-use options and conservation actions Federico M. Pouzols and Atte Moilanen Conservation.
Improving Cybersecurity Through Research & Innovation Dr. Steve Purser Head of Technical Competence Department European Network and Information Security.
Marcel Lavigne, Vice President Business Development November 22nd, 2013 Perth, Australia Deighton Associates Limited The benefits of good pavement management.
CS 678 –Boltzmann Machines1 Boltzmann Machine Relaxation net with visible and hidden units Learning algorithm Avoids local minima (and speeds up learning)
1 Optimization Algorithms on a Quantum Computer A New Paradigm for Technical Computing Richard H. Warren, PhD Optimization.
Simon linke robert. l. pressey robert c. bailey richard h. norris the ecology centre university of queensland australia
Decision Making: An Introduction 1. 2 Decision Making Decision Making is a process of choosing among two or more alternative courses of action for the.
Structure learning with deep neuronal networks 6 th Network Modeling Workshop, 6/6/2013 Patrick Michl.
XCP: Congestion Control for High Bandwidth-Delay Product Network Dina Katabi, Mark Handley and Charlie Rohrs Presented by Ao-Jan Su.
MassConf: Automatic Configuration Tuning By Leveraging User Community Information Computer Science Wei Zheng, Ricardo Bianchini, Thu Nguyen Rutgers University.
Measuring Model Complexity (Textbook, Sections ) CS 410/510 Thurs. April 27, 2007 Given two hypotheses (models) that correctly classify the training.
REES: Reasoning Engines Evaluation Shell version 3.0 Automated Reasoning Lab University of California, Irvine.
1 Pendahuluan Pertemuan 9 Matakuliah: H0062/Teori Sistem Tahun: 2006.
Spatial fisheries management in practice: an example.
Urban Planning Applications of GIS GIS can be applied to many types of problem. Among these are representatives of both raster and vector data base structures,
Reserve design There’s a lot of crap out there We are in a position to inform how to do this intelligently.
Stewart Reid – SSEPD Graham Ault – University of Strathclyde John Reyner – Airwave solutions NINES Project Learning to date.
Marxan Manual Launch Developing better support materials for Marxan and its future developments The New Marxan Manual MEBM Tool Innovation Fund project,
Stevenson and Ozgur First Edition Introduction to Management Science with Spreadsheets McGraw-Hill/Irwin Copyright © 2007 by The McGraw-Hill Companies,
Project Risk Management
Algorithms for Provisioning Virtual Private Networks in the Hose Model Source: Sigcomm 2001, to appear in IEEE/ACM Transactions on Networking Author: Amit.
Advanced Technology for Progressing India's Underground Coal Mining Lisa Duncan August 2014.
Capacity analysis of complex materials handling systems.
Bayesian Sets Zoubin Ghahramani and Kathertine A. Heller NIPS 2005 Presented by Qi An Mar. 17 th, 2006.
Generic Approaches to Model Validation Presented at Growth Model User’s Group August 10, 2005 David K. Walters.
CS212: DATA STRUCTURES Lecture 1: Introduction. What is this course is about ?  Data structures : conceptual and concrete ways to organize data for efficient.
Applying Neural Networks Michael J. Watts
An Introduction to Support Vector Machines (M. Law)
Examination Committee: Dr. Poompat Saengudomlert (Chairperson) Assoc. Prof. Tapio Erke Dr. R.M.A.P. Rajatheva 1 Telecommunications FoS Asian Institute.
Introduction to Software Engineering. Why SE? Software crisis manifested itself in several ways [1]: ◦ Project running over-time. ◦ Project running over-budget.
REDECS ADAPTIVE SHIP MAINTENANCE RESCHEDULING October, 2001 RESIDENCE HOTEL UNITEN KAJANG PATHIAH ABDUL SAMAT (UPM) ALICIA TANG Y. C. (UNITEN)
© Wiley Inc All Rights Reserved. MCSE: Windows Server 2003 Active Directory Planning, Implementation, and Maintenance Study Guide, Second Edition.
Mathematical Models & Optimization?
MARXAN Strategic Conservation Planning by Falk Huettmann.
ECE 466/658: Performance Evaluation and Simulation Introduction Instructor: Christos Panayiotou.
Design an MPI collective communication scheme A collective communication involves a group of processes. –Assumption: Collective operation is realized based.
Linear Models for Classification
Network design Topic 6 Testing and documentation.
From insular protected areas to prioritised biodiversity networks at a landscape level Richard Knight, Fabian Schories & Lorraine Gerrans.
Part 1: Overview of Low Density Parity Check(LDPC) codes.
Channel Islands National Marine Sanctuary: Advancing the Science and Policy of Marine Protected Areas Satie Airame Channel Islands National Marine Sanctuary.
Part-financed by the European Union (European Regional Development Fund) Extension of General Plan of Republic of Lithuania with marine solutions N.Blаžauskas,
MARXAN & MPA: Strategic Conservation Planning by Falk Huettmann.
Discrete optimisation problems on an adiabatic quantum computer
Multi-objective Topology Synthesis and FPGA Prototyping Framework of Application Specific Network-on-Chip m Akram Ben Ahmed Xinyu LI, Omar Hammami.
Why use landscape models?  Models allow us to generate and test hypotheses on systems Collect data, construct model based on assumptions, observe behavior.
Vincenzo Innocente, CERN/EPUser Collections1 Grid Scenarios in CMS Vincenzo Innocente CERN/EP Simulation, Reconstruction and Analysis scenarios.
Learning Kernel Classifiers 1. Introduction Summarized by In-Hee Lee.
1 MIS 444 Information Resource Management Ahituv, Neumann, & Riley Ch. 4: The Systems Approach.
© P. Pongcharoen CCSI/1 Scheduling Complex Products using Genetic Algorithms with Alternative Fitness Functions P. Pongcharoen, C. Hicks, P.M. Braiden.
Regularized Least-Squares and Convex Optimization.
0 TRADE OFFS IN LAND USE PLANNING: A CASE STUDY FROM THE MURCHISON- SEMLIKI LANDSCAPE Dan Segan July 24, 2013.
GIS and High efficiency routing
Applying Neural Networks
10701 / Machine Learning.
Structure learning with deep autoencoders
A brief introduction to neural network
The Last Lecture COMP 512 Rice University Houston, Texas Fall 2003
Systematic conservation plan for cambodia
Systematic conservation plan for Kingdom of Thailand
Software Analysis Tools
Cache - Optimization.
Introduction to Computers
An introduction to neural network and machine learning
Presentation transcript:

the ecology centre university of queensland australia Zonae Cogito - A decision support system for the real world FOSS 4G Conference 2009 Matthew Watts Romola Stewart Daniel Segan Hugh

Software environment Developing countries have limited budgets for Commercial GIS, MapWinGIS Active X control with Delphi and C++, Map Window Open Source GIS

Software evaluation Large data capacity for complex problems Fast and efficient code, O (n log n) (slows down almost linearly as n increases) Systematic validation assures algorithm correctness

View Marxan spatial output

Edit parameters

Simulated annealing dashboard

Assisted parameter calibration

Scenario Editor and Reporter

Simple multiple use zoning

C-Plan interface C-Plan Conservation Planning System

Related R&D Topics Marxan reserve selection software, Alternative objective functions (multiple use zoning, probabilistic threats and occurrences, asymmetric connectivity), Optimisation through Quantum tunneling.

What is Marxan? Ball and Possingham 2000, The most widely used reserve selection software in the world, “Give me a little of everything at the least cost”, limited by binary decision classification.

Where in the world is Marxan?

How simulated annealing works Optimization algorithm; finds configurations with low objective function scores Objective function score has 3 components 1) monetary cost of actions 2) connectivity penalty 3) target penalty A “whole of network” approach to planning

Marxan objective function Minimize subject to Cost + Connectivity + Target Achievement

Asymmetric connectivity The connectivity matrix can be symmetrical for non-directed connections, or asymmetrical for directed connections, Representation of connectivity graph.

Probabilistic treatment Minimize Maximise the probability that a zonation system meets objectives.

Multiple use zoning Minimize subject to and subject to and

What is Marxan with Zones? Enhanced functionality for multiple use zoning, Zones have objectives and constraints, Flexibility to address many planning problems.

Marxan with Zones output Binary configuration3 zone configuration

Marxan with Zones approach Explicit and systematic multiple objectives Simulated annealing algorithm Economic, social, cultural and biological objectives and constraints

Simulated Quantum Annealing Simulate Quantum algorithm on a Turing machine – Quantum Adiabatic Evolution 1,000,000 times faster than simulated thermal annealing?

Quantum tunneling Is a problem amenable to QT? What is the topology of a decision space?

Related Decision Point Articles Decision Point # 28 page 3, “Zonae Cogito - A decision support system for the real world”, Decision Point # 27 page 10, “Marxan with Zones - The world’s most popular conservation planning software just got more relevant”.

Marxan with Zones paper

/ do

Availability and acknowledgements Free software -