Presentation is loading. Please wait.

Presentation is loading. Please wait.

Simulation of Plant Growth using Genetic Algorithms Peter Barber Westminster College.

Similar presentations


Presentation on theme: "Simulation of Plant Growth using Genetic Algorithms Peter Barber Westminster College."— Presentation transcript:

1 Simulation of Plant Growth using Genetic Algorithms Peter Barber Westminster College

2  Initial plan: Strategy Game  Can you design a better plant than “nature”?  Player controls how plant grows  Genetic algorithm dictates how the opponents grow Project Goals

3

4  Revised plan: Proof of Concept Simulation  Time constraints forced changes  Elimination of player interaction & graphics  Goal became to show that genetic algorithms can be used to simulate competition. Project Goals

5 Genetic Algorithm  What is it?  Adaptive heuristic search and optimization algorithm  Mimics genetics & natural selection  How does it work?  Initial solution population  Individuals represented by a genome  Apply the solutions to the problem  Rank the solutions  Individuals rated by a fitness function  Trim the population  Use survivors to populate next generation

6 GAs cont.  How does it work? (cont.)  Crossover  Combine two (or more) genomes  Mutation  Small chance for random mutation of genome  Start over with new generation  Repeat until optimal solution is reached

7 Simulation Details  Simple plant-like structures  Stems & Branches - shape  Leaves - sunlight  Roots - water

8 Simulation cont.  Two-dimensional environment  Sun moves across the sky as the “day” progresses  Plants interact with environment & one another  Leaves cast shadows  Roots compete for water

9

10 Plant Growth  How do the plants grow?  Growth Actions  Extend (Stems, Branches, Roots)  Branch(Stems, Branches, Roots)  Leaf (Branch)  Genome controls choices  Probabilities of growth actions  Structural information  Lengths, angles, etc.  Component properties  Plant properties

11 Growth  Genome Details  Specifics:  Growth specifics  Extend chance  Extend length  Branch chance  Branch angle  Branch location  Properties  Sunlight absorption  Water absorption

12 Growth  Each plant starts as a seed with finite resources  Growth can occur at set intervals  Frequency variable  On grow opportunity:  Chance to refuse growth  Else, traverse plant structure  Every piece has the possibility to take a growth action

13

14 Judging Fitness  Need a way to determine how well a plant performs  Simple solution: resource levels  Plant components collect resources  Plants consume resources:  Passively, by “living”  Actively, by growing  If a plant consumes all its resources, it dies.

15 Resource Spending  Passive consumption  Dependent on total size of plant  Growth consumption  Dependent on several factors  The type of growth (new vs. old)  How much it grows by  The “quality” of the growth

16 Challenges  How to keep plant structure “sane”  Nature is hard to mimic  How to balance resource expenditure  Adjusting values can greatly affect outcome  Unbalancing leads to “cornering” of the algorithm  Goal is to promote competition, not to find loopholes

17 Conclusion  Finish this

18 Real-World Applications  Agricultural simulation  Performance of new crop hybrids  Testing planting patterns  Educational tool  Simple, entertaining version for young children  More complex versions for teaching biology in H.S. and beyond  Entertainment  As initial plan intended

19 Thank You


Download ppt "Simulation of Plant Growth using Genetic Algorithms Peter Barber Westminster College."

Similar presentations


Ads by Google