Causal Research on Soil Temperature and Moisture Content at Different Depths

The soil system is complex and dynamic, making it difficult to understand using traditional statistical approaches. In this paper, we analyze the causal relationship of soil temperature and moisture content at different depths in summer and winter based on dynamic empirical modelling. Specifically, we describe the complexity of soil temperature and moisture content system through mathematical methods. Moreover, we demonstrate the direction and magnitude of causal relationship between soil moisture content and temperature at different depths by equation-free methods. Besides, we describe the difference of soil system properties in summer and winter through causal research. The experiments show that results obtained are consistent with the actual soil environment. The causality is described by dynamic empirical modelling rather than prior soil knowledge. The paper may provide a new idea for soil dynamics research.

[1]  M. Scheffer,et al.  Causal feedbacks in climate change , 2015 .

[2]  Bernhard Scholkopf.  Causality for Machine Learning , 2019 .

[3]  George Sugihara,et al.  Nonlinear forecasting as a way of distinguishing chaos from measurement error in time series , 1990, Nature.

[4]  Donald L DeAngelis,et al.  Equation-free modeling unravels the behavior of complex ecological systems , 2015, Proceedings of the National Academy of Sciences.

[5]  G. Sugihara,et al.  Fluctuating interaction network and time-varying stability of a natural fish community , 2018, Nature.

[6]  Hector Zenil,et al.  Causal deconvolution by algorithmic generative models , 2019, Nature Machine Intelligence.

[7]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[8]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[9]  George Sugihara,et al.  Distinguishing random environmental fluctuations from ecological catastrophes for the North Pacific Ocean , 2005, Nature.

[10]  Wen-Xu Wang,et al.  Reconstructing propagation networks with natural diversity and identifying hidden sources , 2014, Nature Communications.

[11]  G. Dur,et al.  Planktivorous fish predation masks anthropogenic disturbances on decadal trends in zooplankton biomass and body size structure in Lake Biwa, Japan , 2019, Limnology and Oceanography.

[12]  George Sugihara,et al.  Detecting Causality in Complex Ecosystems , 2012, Science.

[13]  Bernhard Schölkopf,et al.  Inferring causation from time series in Earth system sciences , 2019, Nature Communications.

[14]  Yu Xie,et al.  Population heterogeneity and causal inference , 2013, Proceedings of the National Academy of Sciences.

[15]  Vladlen Koltun,et al.  An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling , 2018, ArXiv.

[16]  Ciarán M Lee,et al.  Improving the accuracy of medical diagnosis with causal machine learning , 2020, Nature Communications.

[17]  George Sugihara,et al.  Predicting climate effects on Pacific sardine , 2013, Proceedings of the National Academy of Sciences.

[18]  George Sugihara,et al.  Nonlinear forecasting for the classification of natural time series , 1994, Philosophical Transactions of the Royal Society of London. Series A: Physical and Engineering Sciences.

[19]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[20]  George Sugihara,et al.  Spatial convergent cross mapping to detect causal relationships from short time series. , 2015, Ecology.

[21]  Chih-hao Hsieh,et al.  Empirical dynamic modeling for beginners , 2017, Ecological Research.

[22]  Dino Sejdinovic,et al.  Detecting and quantifying causal associations in large nonlinear time series datasets , 2017, Science Advances.

[23]  Renato Renner,et al.  Discovering physical concepts with neural networks , 2018, Physical review letters.

[24]  Eric A Sobie,et al.  An Introduction to Dynamical Systems , 2011, Science Signaling.

[25]  Jiang Bian,et al.  Causal inference and counterfactual prediction in machine learning for actionable healthcare , 2020, Nature Machine Intelligence.

[26]  H. Ye,et al.  Information leverage in interconnected ecosystems: Overcoming the curse of dimensionality , 2016, Science.

[27]  Hal R Varian,et al.  Causal inference in economics and marketing , 2016, Proceedings of the National Academy of Sciences.

[28]  H. Okamura,et al.  Climate change and interspecific interactions drive species alternations between anchovy and sardine in the western North Pacific: Detection of causality by convergent cross mapping , 2018 .

[29]  Katsuhiko Yoshida,et al.  Liberation from equations: An equation-free method reveals the ecological interaction networks , 2016 .

[30]  C. Granger.  Investigating causal relations by econometric models and cross-spectral methods , 1969 .

[31]  George Sugihara,et al.  Equation-free mechanistic ecosystem forecasting using empirical dynamic modeling , 2015, Proceedings of the National Academy of Sciences.

[32]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[33]  Y. Onoda,et al.  Core microbiomes for sustainable agroecosystems , 2018, Nature Plants.

[34]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[35]  Wojciech Zaremba,et al.  Recurrent Neural Network Regularization , 2014, ArXiv.

[36]  Robert E. White,et al.  Principles and practice of soil science : the soil as a natural resource , 1997 .

[37]  Mélanie Frappier,et al.  The Book of Why: The New Science of Cause and Effect , 2018, Science.