An Artificial Intelligence Approach to Predict Gross Primary Productivity in the Forests of South Korea Using Satellite Remote Sensing Data

Lee, Bora; Kim, Nari; Kim, Eun-Sook; Jang, Keunchang; Kang, Minseok; Lim, Jong-Hwan; Cho, Jaeil; Lee, Yang-Won

doi:10.3390/f11091000

Cited by 22 publications

(14 citation statements)

References 45 publications

(65 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using machine leaning approaches is increasingly common in biological research, for instance, to infer the intraspecific genetic diversity of amphibian taxa or predict the conservation status of data-deficient mammals (Bland et al, 2014;Barrow et al, 2020;Lee et al, 2020). More specifically, using machine learning to assist conservation prioritization is an active field of development (Walker et al, 2020;Cazalis et al, 2022;Silvestro et al, 2022;Zizka et al, 2022a), and automated methods have the potential to process large numbers of species quickly (Pelletier et al, 2018;Zizka et al, 2021b).…”

Section: Discussionmentioning

confidence: 99%

Global Estimation and Mapping of the Conservation Status of Tree Species Using Artificial Intelligence

et al. 2022

View full text Add to dashboard Cite

Trees are fundamental for Earth’s biodiversity as primary producers and ecosystem engineers and are responsible for many of nature’s contributions to people. Yet, many tree species at present are threatened with extinction by human activities. Accurate identification of threatened tree species is necessary to quantify the current biodiversity crisis and to prioritize conservation efforts. However, the most comprehensive dataset of tree species extinction risk—the Red List of the International Union for the Conservation of Nature (IUCN RL)—lacks assessments for a substantial number of known tree species. The RL is based on a time-consuming expert-based assessment process, which hampers the inclusion of less-known species and the continued updating of extinction risk assessments. In this study, we used a computational pipeline to approximate RL extinction risk assessments for more than 21,000 tree species (leading to an overall assessment of 89% of all known tree species) using a supervised learning approach trained based on available IUCN RL assessments. We harvested the occurrence data for tree species worldwide from online databases, which we used with other publicly available data to design features characterizing the species’ geographic range, biome and climatic affinities, and exposure to human footprint. We trained deep neural network models to predict their conservation status, based on these features. We estimated 43% of the assessed tree species to be threatened with extinction and found taxonomic and geographic heterogeneities in the distribution of threatened species. The results are consistent with the recent estimates by the Global Tree Assessment initiative, indicating that our approach provides robust and time-efficient approximations of species’ IUCN RL extinction risk assessments.

show abstract

Section: Discussionmentioning

confidence: 99%

Global Estimation and Mapping of the Conservation Status of Tree Species Using Artificial Intelligence

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Sample plot inventory [44], model inversion [45], and flux observation [46] are included in this category. Simple AI methods have been extensively applied for NPP estimation over large scales as well [47]- [50]. However, simple AI models yield quite different results from traditional methods, so their validity is questionable; simple AI models are more controversial in terms of NPP estimation [26].…”

Section: A Carbon Neutralization In Citymentioning

confidence: 99%

A Spatio-Temporal Neural Network Learning System for City-Scale Carbon Storage Capacity Estimating

et al. 2023

View full text Add to dashboard Cite

Carbon storage capacity can be estimated to establish evaluation standards and statistics for carbon neutrality. Existing estimation methods including machine learning system have weakness modeling ability, and they are unable to deal with the complex topographies and temporal changes in vegetation in urban zones. However, a deep neural network has the potential ability to face such complex scenes because of its nonlinear fitting properties which has been widely used in industry. In this study, a novel and powerful neural network learning system named CiSL-NPP is proposed, to integrate multi-source data as an accurate, efficient, simple, long-term, city-scale carbon storage capacity measurement method. We use an unsupervised generation model spatio-temporal Masked AutoEncoder (st-MAE) and lightweight RNN model to efficiently obtain high-quality data that contain time-series information such as seasons; this minimizes any undue impact of meteorological, temporal, and spatial factors on the measurement owing to the multi-source, multi-modal nature of the data. In the MAE, we add seasonal coding to make it time-series sensitive; we also embed road network information to accurately perceive the complex topography of the city. Results for 16 cities in China and Europe revealed that the proposed method shows: 1) Higher-quality generated data (MSE is 0.13-0.29); 2) Accurate coverage of time series and complex geographical features; 3) Satisfaction of estimation demands with only 316 RMB cost; 4) Capability to evolve a long-term trend of urban vegetation carbon storage capacity in 4.2 days; and 5) Easily interpretable results which could, in practice, provide sound guidance for urban planning and decision-making processes. INDEX TERMSNeural network Learning System, Unsupervised generation model, Spatio-temporal Masked AutoEncoder, Carbon Storage Capacity Measurement I. INTRODUCTION M ORE than 90% of human economic activity takes place in cities [1], which directly contribute at least 85% of global carbon emissions [2] and are regarded as the world's main battlefields of carbon neutrality [3]. Currently, carbon mitigation and carbon sink increment are the primary approaches to achieving urban carbon neutrality. The carbon mitigation approach, a complex systematic undertaking, is difficult to implement [4]. Further, strict policies towards emissions may have consequences such as carbon leakage [5], [6]. The carbon sink increment approach shows more potential to achieve urban carbon neutrality. For example, studies indicate that the carbon sink of urban vegetation can offset more than 22.45% of carbon emissions [7], already achieving carbon neutrality in some areas [8]. In city, limited to a fixed-size space, the effective way to increase carbon sink is to use green resources (e.g., municipal parks) rationally according to their vegetation carbon storage capacity. Net Primary Productivity (NPP), a crucial metric reflecting the storage effect of vegetation , is the key role for increasing carbon storage capacity in the city ...

show abstract

“…Recently, deep learning models, such as deep neural networks (DNN), which are an extension of traditional ANN models with multiple hidden layers, have become popular for predictive modelling (LeCun et al, 2015; Lee et al, 2020; Reichstein et al, 2019; Yuan et al, 2020). Outputs generated using deep learning models outperformed other machine learning models in many cases due to their ability to identify complex non‐linear relations between the dependent and independent variables (Beysolow II, 2017; Tamiminia et al, 2021; Zhang et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

“…Essentially, machine learning modelling equations cannot be observed, limiting their ability to reliably map results for the whole study area (Ali et al, 2014;Jin et al, 2020;Lee et al, 2020). Recently, use of Google earth engine (GEE)-assisted with the Tensorflow platform enables mapping of vegetation AGB (de la Gorelick et al, 2017;Hancher, 2017).…”

mentioning

confidence: 99%

Improving the accuracy of models to map alpine grassland above‐ground biomass using Google earth engine

Yan

Gao

Brierley

et al. 2023

Grass and Forage Science

View full text Add to dashboard Cite

Accurate modelling and mapping of alpine grassland aboveground biomass (AGB) are crucial for pastoral agriculture planning and management on the Qinghai Tibet Plateau (QTP). This study assessed the effectiveness of four popular models (traditional multiple linear regression (MLR), support vector machine (SVM), artificial neural network (ANN), and deep neural network (DNN)) with various input combinations (geospatial variables [GV], vegetation types [VT], field measurements [FM], meteorological variables [MV] and observation time [OT]) for AGB estimation based on a new framework for AGB modelling and mapping using Google Earth Engine. The results showed that the input feature of GV had a poor performance in AGB estimation (0.121 < R2 < 0.591). FM improved the accuracy the most when incorporated with GV (0.815 < R2 < 0.833). Although MV, VT and OT improved the accuracy (R2) only by 0.112–0.216 with an importance rank order of MV > VT > OT for machine learning models, their outputs could be used to map AGB. Grass AGB was less accurately predicted than shrub AGB, but the pooling of both VTs improved estimation accuracy (R2) by 0.171–0.269. The performance of the models followed the ranked order of DNN > ANN > SVM > MLR. DNN had the highest accuracy (R2 = 0.818) using all non‐field measured variables (excluding FM) as the inputs, and it was successfully applied to a new dataset (not associated with the data used in the training and testing) with a R2 of 0.676. This study presents an effective and operational framework for modelling and mapping grassland AGB. Accordingly, it provides the scientific foundations to determine of sustainable grazing carrying capacity in alpine grasslands.

show abstract

An Artificial Intelligence Approach to Predict Gross Primary Productivity in the Forests of South Korea Using Satellite Remote Sensing Data

Cited by 22 publications

References 45 publications

Global Estimation and Mapping of the Conservation Status of Tree Species Using Artificial Intelligence

Global Estimation and Mapping of the Conservation Status of Tree Species Using Artificial Intelligence

A Spatio-Temporal Neural Network Learning System for City-Scale Carbon Storage Capacity Estimating

Improving the accuracy of models to map alpine grassland above‐ground biomass using Google earth engine

Contact Info

Product

Resources

About