Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Oct 20;13(10):e10626.
doi: 10.1002/ece3.10626. eCollection 2023 Oct.

INTRAGRO: A machine learning approach to predict future growth of trees under climate change

Sugam Aryal  1 , Jussi Grießinger  1 , Nita Dyola  2   3 , Narayan Prasad Gaire  4 , Tribikram Bhattarai  5 , Achim Bräuning  1
Affiliations

INTRAGRO: A machine learning approach to predict future growth of trees under climate change

Sugam Aryal et al. Ecol Evol. .

Abstract

The escalating impact of climate change on global terrestrial ecosystems demands a robust prediction of the trees' growth patterns and physiological adaptation for sustainable forestry and successful conservation efforts. Understanding these dynamics at an intra-annual resolution can offer deeper insights into tree responses under various future climate scenarios. However, the existing approaches to infer cambial or leaf phenological change are mainly focused on certain climatic zones (such as higher latitudes) or species with foliage discolouration during the fall season. In this study, we demonstrated a novel approach (INTRAGRO) to combine intra-annual circumference records generated by dendrometers coupled to the output of climate models to predict future tree growth at intra-annual resolution using a series of supervised and unsupervised machine learning algorithms. INTRAGRO performed well using our dataset, that is dendrometer data of P. roxburghii Sarg. from the subtropical mid-elevation belt of Nepal, with robust test statistics. Our growth prediction shows enhanced tree growth at our study site for the middle and end of the 21st century. This result is remarkable since the predicted growing season by INTRAGRO is expected to shorten due to changes in seasonal precipitation. INTRAGRO's key advantage is the opportunity to analyse changes in trees' intra-annual growth dynamics on a global scale, regardless of the investigated tree species, regional climate and geographical conditions. Such information is important to assess tree species' growth performance and physiological adaptation to growing season change under different climate scenarios.

Keywords: Pinus roxburghii; dendrometer; growing‐season change; intra‐annual growth; machine learning algorithm; sub‐tropical Nepal.

PubMed Disclaimer

Figures

FIGURE 1
FIGURE 1
Daily resolved temperature and precipitation of the study area along with the temporal distribution and duration of periods with consecutive dry days. Prec, daily precipitation; Tavg, daily average temperature.
FIGURE 2
FIGURE 2
Overall workflow of the INTRAGRO approach. CMs, climate models.
FIGURE 3
FIGURE 3
Dendrometer time series of the four studied trees from April 2016 to October 2021.
FIGURE 4
FIGURE 4
Pattern of daily stem circumference variations in mm for the four clusters: cluster0, cluster1, cluster2 and cluster3. The numbers in brackets represent the total number of daily cycles. HH, hours.
FIGURE 5
FIGURE 5
Intra‐annual (a) and inter‐annual (b) distribution of stem diameter variation clusters in the observed period. The lower panel represents the monthly temperature and precipitation averaged for 2016–2020 (c) and the annual pattern of monthly temperature and precipitation for each year from 2016 to 2020 (d).
FIGURE 6
FIGURE 6
Temperature (a, b) and precipitation (c) conditions for the four clusters 0–3 of stem circumference variations. Different letters in the clusters represent significant differences at the p < .05 level based on the Kruskal‐Wallis test followed by Dunn's post hoc test analysis. The horizontal lines represent the overall mean, and the green points in each cluster represent the average climate of each cluster. Cls0 = cluster0; Cls1 = cluster1; Cls2 = cluster2; Cls3 = cluster3; Tmin = Minimum temperature; Tmax = Maximum temperature; and Prec = Precipitation.
FIGURE 7
FIGURE 7
Modelled distribution of stem circumference variation clusters (DSCCs) under different climate change scenarios. The graphs in columns A and B represent the predicted distribution of DSCCs in the 2050s and 2100s. Column C represents the proportions of DSCCs 0–3 in different climate change scenarios. In the concentric diagram, the inner, middle and outer circular layers represent the observed period (2016–2021) and the predicted periods 2048–2053 and 2095–2100 for different Shared Socio‐economic Pathways (SSPs).
FIGURE 8
FIGURE 8
Comparison of observed and simulated monthly circumferences.
FIGURE 9
FIGURE 9
Predicted tree growth in the 2050s and 2100s under different climate change scenarios.
FIGURE 10
FIGURE 10
Annual circumferential growth patterns in the observed (Obs.) and modelled periods for different scenarios: (a) the 2050s and (b) the 2100s. The solid lines represent cumulative growth scaled in the left y‐axis, and the dashed lines represent the daily growth rate mounted in the right y‐axis. The vertical straight lines represent the beginning and cessation of the growing seasons, respectively. The x‐axis represents the day of the year (DOY). (c) and (d) represent the difference between the daily circumference change (DCC) rate in modelled and observation periods for the 2050s and 2100s, respectively, and (e) represents the difference between the DCC rate in the 2050s and 2100s.
See this image and copyright information in PMC

References

    1. Althnian, A. , AlSaeed, D. , Al‐Baity, H. , Samha, A. , Dris, A. B. , Alzakari, N. , Abou Elwafa, A. , & Kurdi, H. (2021). Impact of dataset size on classification performance: An empirical evaluation in the medical domain. Applied Sciences, 11, 796.
    1. Alves, E. S. , & Angyalossy‐Alfonso, V. (2000). Ecological trends in the wood anatomy of some Brazilian species. 1. Growth rings and vessels. IAWA Journal, 21, 3–30.
    1. Anchukaitis, K. J. , Evans, M. N. , Kaplan, A. , Vaganov, E. A. , Hughes, M. K. , Grissino‐Mayer, H. D. , & Cane, M. A. (2006). Forward modeling of regional scale tree‐ring patterns in the southeastern United States and the recent influence of summer drought. Geophysical Research Letters, 33, 1–4.
    1. Aryal, S. , Bhuju, D. R. , Kharal, D. K. , Gaire, N. P. , & Dyola, N. (2018). Climatic upshot using growth pattern of Pinus roxburghii from western Nepal. Pakistan Journal of Botany, 50, 579–588.
    1. Aryal, S. , Gaire, N. P. , Pokhrel, N. R. , Rana, P. , Sharma, B. , Kharal, D. K. , Poudel, B. S. , Dyola, N. , Fan, Z.‐X. , Grießinger, J. , & Bräuning, A. (2020). Spring season in Western Nepal Himalaya is not yet warming: A 400‐year temperature reconstruction based on tree‐ring widths of Himalayan hemlock (Tsuga dumosa). Atmosphere, 11, 132.

LinkOut - more resources