Understanding Climate-Vegetation Interactions in Global Rainforests Through a GP-Tree Analysis

The tropical rainforests are the largest reserves of terrestrial carbon and therefore, the future of these rainforests is a question that is of immense importance in the geoscience research community. With the recent severe Amazonian droughts in 2005 and 2010 and on-going drought in the Congo region for more than two decades, there is growing concern that these forests could succumb to precipitation reduction, causing extensive carbon release and feedback to the carbon cycle. However, there is no single ecosystem model that quantifies the relationship between vegetation health in these rainforests and climatic factors. Small scale studies have used statistical correlation measure and simple linear regression to model climate-vegetation interactions, but suffer from the lack of comprehensive data representation as well as simplistic assumptions about dependency of the target on the covariates. In this paper we use genetic programming (GP) based symbolic regression for discovering equations that govern the vegetation climate dynamics in the rainforests. Expecting micro-regions within the rainforests to have unique characteristics compared to the overall general characteristics, we use a modified regression-tree based hierarchical partitioning of the space to build individual models for each partition. The discovery of these equations reveal very interesting characteristics about the Amazon and the Congo rainforests. Our method GP-tree shows that the rainforests exhibit tremendous resiliency in the face of extreme climatic events by adapting to changing conditions.

[1]  J. R. Quinlan.  Learning With Continuous Classes , 1992 .

[2]  Kun Mao,et al.  Estimating relationships between NDVI and climate change in Guizhou Province, Southwest China , 2010, 2010 18th International Conference on Geoinformatics.

[3]  R. Betts,et al.  Acceleration of global warming due to carbon-cycle feedbacks in a coupled climate model , 2000, Nature.

[4]  R. Myneni,et al.  The interpretation of spectral vegetation indexes , 1995 .

[5]  Lior Rokach,et al.  Top-down induction of decision trees classifiers - a survey , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[6]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[7]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[8]  Hod Lipson,et al.  Age-fitness pareto optimization , 2010, GECCO '10.

[9]  Maosheng Zhao,et al.  Drought-Induced Reduction in Global Terrestrial Net Primary Production from 2000 Through 2009 , 2010, Science.

[10]  J. Terborgh,et al.  The regional variation of aboveground live biomass in old‐growth Amazonian forests , 2006 .

[11]  Berthold K. P. Horn,et al.  Hill shading and the reflectance map , 1981, Proceedings of the IEEE.

[12]  Aaron Moody,et al.  Geographical distribution of global greening trends and their climatic correlates: 1982–1998 , 2005 .

[13]  Sean C. Thomas,et al.  Increasing carbon storage in intact African tropical forests , 2009, Nature.

[14]  P. Ciais,et al.  Widespread decline of Congo rainforest greenness in the past decade , 2014, Nature.

[15]  Dick den Hertog,et al.  Order of Nonlinearity as a Complexity Measure for Models Generated by Symbolic Regression via Pareto Genetic Programming , 2009, IEEE Transactions on Evolutionary Computation.

[16]  A. Huete,et al.  Amazon Forests Green-Up During 2005 Drought , 2007, Science.

[17]  C. Tucker,et al.  Climate-Driven Increases in Global Terrestrial Net Primary Production from 1982 to 1999 , 2003, Science.

[18]  S. Ganguly,et al.  Widespread decline in greenness of Amazonian vegetation due to the 2010 drought , 2011 .

[19]  F. Yuan,et al.  Analysis of the relationship between NDVI and climate variables in minnesota using geographically weighted regression and spatial interpolation , 2007 .