4.7 Article

From spectra to plant functional traits: Transferable multi-trait models from heterogeneous and sparse data

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Ecology

Assessing and improving the transferability of current global spatial prediction models

Marvin Ludwig et al.

Summary: Global-scale maps of the environment are crucial for researchers and decision makers, but the feasibility of making predictions beyond the training data location has been questioned. We propose a new workflow that combines recent developments in spatial predictive mapping to improve model transferability and performance assessment. However, the limited availability of reference data hampers the creation and evaluation of reliable gap-free global predictions.

GLOBAL ECOLOGY AND BIOGEOGRAPHY (2023)

Article Ecology

Nearest neighbour distance matching Leave-One-Out Cross-Validation for map validation

Carles Mila et al.

Summary: This study proposes a new cross-validation strategy that takes into account the geographical prediction space and compares it with other established methods. The new method, called NNDM LOO CV, provides reliable estimates in all scenarios considered. The existing methods, LOO and bLOO CV, have limitations and only provide accurate estimates in certain situations. Therefore, considering the geographical prediction space is essential when designing map validation methods.

METHODS IN ECOLOGY AND EVOLUTION (2022)

Article Computer Science, Artificial Intelligence

A Survey on Multi-Task Learning

Yu Zhang et al.

Summary: This paper provides a survey of Multi-Task Learning (MTL) from the perspective of algorithmic modeling, applications, and theoretical analyses. It discusses different MTL algorithms and their characteristics, as well as the combination of MTL with other learning paradigms. The paper also reviews MTL models for large-scale tasks or high-dimensional data, as well as dimensionality reduction and feature hashing. Real-world applications of MTL are examined, and theoretical analyses and future directions are discussed.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2022)

Review Plant Sciences

Plant spectra as integrative measures of plant phenotypes

Shan Kothari et al.

Summary: Spectroscopy has been widely used in plant ecology to infer plant traits and processes at individual or community levels. However, understanding the phenotypic information contained in spectra can be challenging due to the complexity of structural and chemical factors. Different approaches, such as radiative transfer and empirical models, have been used to estimate plant traits from spectra, each with their strengths and limitations. In addition, treating spectral data as analogous to trait space can provide valuable insights into the processes structuring plant communities, although it may be more difficult to interpret specific biological processes.

JOURNAL OF ECOLOGY (2022)

Article Geography, Physical

Retrieval of carbon content and biomass from hyperspectral imagery over cultivated areas

Matthias Wocher et al.

Summary: Spaceborne imaging spectroscopy is a valuable data source for agricultural management and research. This study presents a workflow for inferring crop carbon content and biomass from EnMAP data, using a combination of radiative transfer modeling and machine learning regression algorithms. The proposed models demonstrate promising reliability for cultivated areas.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2022)

Review Environmental Sciences

Multi-sensor spectral synergies for crop stress detection and monitoring in the optical domain: A review

Katja Berger et al.

Summary: This study provides an overview of the main spectral technologies and retrieval approaches for detecting crop stress in agriculture. Remote sensing technology can capture different plant responses under stress through specific light interaction processes. The analysis of research papers reveals the increasing usage of satellite and unmanned aerial vehicle data and a shift towards more advanced models. However, most studies still focus on proxies calculated from single-source sensor domains, and future research should explore simultaneous analysis of multiple stress responses, integration of multi-domain models and machine learning methods, and assimilation of estimated plant traits into integrated crop growth models.

REMOTE SENSING OF ENVIRONMENT (2022)

Article Biodiversity Conservation

Evaluating different methods for retrieving intraspecific leaf trait variation from hyperspectral leaf reflectance

Kenny Helsen et al.

Summary: Leaf mass per area (LMA), leaf dry matter content (LDMC) and leaf water content/ equivalent water thickness (EWT) are commonly used functional plant traits in ecology, and spectroscopy has proven to be a powerful tool to collect such trait information. However, the accuracy of reflectance-based trait predictions may vary across different plant species, with species-specific PLSR models showing the highest correlation accuracy.

ECOLOGICAL INDICATORS (2021)

Article Environmental Sciences

PROSPECT-PRO for estimating content of nitrogen-containing leaf proteins and other carbon-based constituents

Jean-Baptiste Feret et al.

Summary: A new PROSPECT-PRO model was developed to accurately differentiate nitrogen-based constituents from carbon-based constituents and estimate foliar protein content from optical properties of vegetation. The model performed well across various plant samples and showed promising potential for involvement in precision agriculture and ecological applications.

REMOTE SENSING OF ENVIRONMENT (2021)

Article Biodiversity Conservation

Hyperspectral retrieval of leaf physiological traits and their links to ecosystem productivity in grassland monocultures

Yujin Zhao et al.

Summary: Plant functional traits are closely linked to ecological processes and ecosystem functions. Recent studies have shown that plant physiological traits can be accurately derived from hyperspectral images. The prediction accuracy of physiological traits based on area or mass metrics was compared using remote sensing approaches, with area-based traits showing higher accuracy. Canopy physiological traits were successfully mapped and related to ecosystem productivity using UAV-based spectrometry, providing insight into the relationship between functional traits and ecosystem functions.

ECOLOGICAL INDICATORS (2021)

Article Biodiversity Conservation

The retrieval of plant functional traits from canopy spectra through RTM-inversions and statistical models are both critically affected by plant phenology

Felix Schiefer et al.

Summary: Plant phenology has a significant impact on the predictive performance of both statistical and RTM-based methods for retrieving plant functional traits, and the effects vary between different traits.

ECOLOGICAL INDICATORS (2021)

Article Multidisciplinary Sciences

The three major axes of terrestrial ecosystem function

Mirco Migliavacca et al.

Summary: The leaf economics spectrum and the global spectrum of plant forms and functions revealed fundamental axes of variation in plant traits, representing different ecological strategies shaped by the evolutionary development of plant species. Ecosystem functions depend on environmental conditions and the traits of species within ecological communities. However, the axes of variation of ecosystem functions are largely unknown, limiting our understanding of ecosystem responses to anthropogenic drivers and environmental changes.

NATURE (2021)

Review Geography, Physical

Review on Convolutional Neural Networks (CNN) in vegetation remote sensing

Teja Kattenborn et al.

Summary: Identifying and characterizing vascular plants in time and space is essential for various disciplines such as forestry, conservation, and agriculture. Remote sensing technology, specifically utilizing deep learning methods like Convolutional Neural Networks (CNN), is crucial in improving efficiency and accuracy in extracting vegetation properties from remote sensing imagery. The modularity and flexibility of CNN frameworks allow for adaptation to different architectures, particularly for multi-modal or multi-temporal applications, ultimately leading to a new era of vegetation remote sensing.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2021)

Article Geography, Physical

Efficient RTM-based training of machine learning regression algorithms to quantify biophysical & biochemical traits of agricultural crops

Martin Danner et al.

Summary: The study investigated the potential of a scientific processor using EnMAP satellite spectroscopic imagery to quantify crop traits, finding that a hybrid retrieval workflow based on machine learning models and synthetic vegetation spectra lookup table provides efficient and accurate estimation of biophysical and biochemical variables, with ANN models showing the best performance.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2021)

Article Biochemical Research Methods

Wheat physiology predictor: predicting physiological traits in wheat from hyperspectral reflectance measurements using deep learning

Robert T. Furbank et al.

Summary: The study demonstrates that the accuracy of predicting wheat photosynthetic and leaf traits using deep learning and ensemble models can be improved compared to PLSR without overfitting. These models can be flexibly applied across different spectral ranges without compromising accuracy.

PLANT METHODS (2021)

Article Plant Sciences

Source:sink imbalance detected with leaf- and canopy-level spectroscopy in a field-grown crop

Angela C. Burnett et al.

Summary: This study found that zucchini grown under carbon sink limitation exhibited different metabolic profiles, which could be analyzed non-destructively using hyperspectral reflectance. Partial least-squares regression models linked functional traits with reflectance data, enabling high-throughput estimation and rapid detection of sink limitation in growth responses.

PLANT CELL AND ENVIRONMENT (2021)

Article Environmental Sciences

Field spectroscopy of canopy nitrogen concentration in temperate grasslands using a convolutional neural network

R. R. Pullanagari et al.

Summary: This study developed season-specific and spectral-region-specific 1D-CNN models using deep learning techniques for timely and accurate estimation of canopy nitrogen concentration. Results showed that the 1D-CNN model exhibited higher accuracy on the independent validation dataset, while the full spectral range model outperformed the spectral region-specific models in terms of accuracy.

REMOTE SENSING OF ENVIRONMENT (2021)

Review Environmental Sciences

NASA's surface biology and geology designated observable: A perspective on surface imaging algorithms

Kerry Cawse-Nicholson et al.

Summary: The paper summarizes the Surface Biology and Geology (SBG) as a Designated Targeted Observable (DO) recommended in the 2017-2027 National Academies' Decadal Survey, focusing on agriculture, natural habitats, water use/quality, and urban development. It reviews existing algorithms in each category and synthesizes the findings of over 130 scientists.

REMOTE SENSING OF ENVIRONMENT (2021)

Article Geography, Physical

Mapping landscape canopy nitrogen content from space using PRISMA data

Jochem Verrelst et al.

Summary: This work presents the first hybrid model for canopy nitrogen content retrieval from spaceborne imaging spectroscopy data. The model combines physically-based models, machine learning regression algorithms, and active learning techniques, achieving promising results in quantifying CNC from space and demonstrating feasibility for routine application in operational contexts.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2021)

Article Environmental Sciences

The PRISMA imaging spectroscopy mission: overview and first performance analysis

S. Cogliati et al.

Summary: The PRISMA satellite mission, launched in March 2019, is a cutting-edge imaging spectroscopy mission for Earth Observation. The mission conducted field and airborne campaigns in an agriculture area in Italy to assess instrument performance and data product consistency. The results show that the PRISMA satellite images are suitable for further scientific applications, but further studies are needed to confirm performance in other land cover types.

REMOTE SENSING OF ENVIRONMENT (2021)

Article Ecology

Predicting into unknown space? Estimating the area of applicability of spatial prediction models

Hanna Meyer et al.

Summary: Machine learning algorithms are popular for spatial mapping due to their ability to fit complex relationships, but their use is limited to data similar to the training set. The study proposes a method to assess the area where a prediction model can be reliably applied, using a Dissimilarity Index (DI) to define the Area of Applicability (AOA) and map estimated performance. Simulation studies show comparable prediction errors within the AOA to cross-validation errors, emphasizing the importance of considering the relationship between DI and cross-validation performance.

METHODS IN ECOLOGY AND EVOLUTION (2021)

Article Biodiversity Conservation

TRY plant trait database - enhanced coverage and open access

Jens Kattge et al.

GLOBAL CHANGE BIOLOGY (2020)

Article Geochemistry & Geophysics

Quantifying Vegetation Biophysical Variables from Imaging Spectroscopy Data: A Review on Retrieval Methods

Jochem Verrelst et al.

SURVEYS IN GEOPHYSICS (2019)

Article Geochemistry & Geophysics

Spaceborne Imaging Spectroscopy for Sustainable Agriculture: Contributions and Challenges

Tobias B. Hank et al.

SURVEYS IN GEOPHYSICS (2019)

Article Environmental Sciences

Mapping foliar functional traits and their uncertainties across three years in a grassland experiment

Zhihui Wang et al.

REMOTE SENSING OF ENVIRONMENT (2019)

Article Ecology

A novel procedure for measuring functional traits of herbaceous species through field spectroscopy

Elisa Van Cleemput et al.

METHODS IN ECOLOGY AND EVOLUTION (2019)

Article Multidisciplinary Sciences

Radiative transfer modelling reveals why canopy reflectance follows function

Teja Kattenborn et al.

SCIENTIFIC REPORTS (2019)

Article Environmental Sciences

Advantages of retrieving pigment content [μg/cm2] versus concentration [%] from canopy reflectance

Teja Kattenborn et al.

REMOTE SENSING OF ENVIRONMENT (2019)

Review Chemistry, Medicinal

A Survey of Multi-task Learning Methods in Chemoinformatics

Sergey Sosnin et al.

MOLECULAR INFORMATICS (2019)

Article Ecology

Differentiating plant functional types using reflectance: which traits make the difference?

Teja Kattenborn et al.

REMOTE SENSING IN ECOLOGY AND CONSERVATION (2019)

Article Chemistry, Multidisciplinary

A quantitative uncertainty metric controls error in neural network-driven chemical discovery

Jon Paul Janet et al.

CHEMICAL SCIENCE (2019)

Article Plant Sciences

Hyperspectral reflectance as a tool to measure biochemical and physiological traits in wheat

Viridiana Silva-Perez et al.

JOURNAL OF EXPERIMENTAL BOTANY (2018)

Review Multidisciplinary Sciences

A brief introduction to weakly supervised learning

Zhi-Hua Zhou

NATIONAL SCIENCE REVIEW (2018)

Article Automation & Control Systems

Modern practical convolutional neural networks for multivariate regression: Applications to NIR calibration

Chenhao Cui et al.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2018)

Article Environmental Sciences

LiDAR derived forest structure data improves predictions of canopy N and P concentrations from imaging spectroscopy

Michael Ewald et al.

REMOTE SENSING OF ENVIRONMENT (2018)

Article Environmental Sciences

An Approach for Foliar Trait Retrieval from Airborne Imaging Spectroscopy of Tropical Forests

Roberta E. Martin et al.

REMOTE SENSING (2018)

Article Environmental Sciences

Physically-Based Retrieval of Canopy Equivalent Water Thickness Using Hyperspectral Data

Matthias Wocher et al.

REMOTE SENSING (2018)

Article Biochemistry & Molecular Biology

Machine Learning Techniques for Predicting Crop Photosynthetic Capacity from Leaf Reflectance Spectra

David Heckmann et al.

MOLECULAR PLANT (2017)

Article Environmental Sciences

PROSPECT-D: Towards modeling leaf optical properties through a complete lifecycle

J. -B. Feret et al.

REMOTE SENSING OF ENVIRONMENT (2017)

Article Geochemistry & Geophysics

Deep Learning in Remote Sensing

Xiao Xiang Zhu et al.

IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE (2017)

Article Multidisciplinary Sciences

The global spectrum of plant form and function

Sandra Diaz et al.

NATURE (2016)

Article Computer Science, Interdisciplinary Applications

Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

Hoo-Chang Shin et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2016)

Article Environmental Sciences

Fluspect-B: A model for leaf fluorescence, reflectance and transmittance spectra

Nastassia Vilfan et al.

REMOTE SENSING OF ENVIRONMENT (2016)

Article Environmental Sciences

Organismic-Scale Remote Sensing of Canopy Foliar Traits in Lowland Tropical Forests

K. Dana Chadwick et al.

REMOTE SENSING (2016)

Review Biodiversity Conservation

Spectranomics: Emerging science and conservation opportunities at the interface of biodiversity and remote sensing

Gregory P. Asner et al.

GLOBAL ECOLOGY AND CONSERVATION (2016)

Article Geography, Physical

From plant functional types to plant functional traits: A new paradigm in modelling global vegetation dynamics

Yanzheng Yang et al.

PROGRESS IN PHYSICAL GEOGRAPHY-EARTH AND ENVIRONMENT (2015)

Article Environmental Sciences

Quantifying forest canopy traits: Imaging spectroscopy versus field survey

Gregory P. Asner et al.

REMOTE SENSING OF ENVIRONMENT (2015)

Review Environmental Sciences

The EnMAP Spaceborne Imaging Spectroscopy Mission for Earth Observation

Luis Guanter et al.

REMOTE SENSING (2015)

Article Geochemistry & Geophysics

Optimizing LUT-Based RTM Inversion for Semiautomatic Mapping of Crop Biophysical Parameters from Sentinel-2 and-3 Data: Role of Cost Functions

Jochem Verrelst et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2014)

Article Plant Sciences

Using leaf optical properties to detect ozone effects on foliar biochemistry

Elizabeth A. Ainsworth et al.

PHOTOSYNTHESIS RESEARCH (2014)

Review Ecology

Review of optical-based remote sensing for plant trait mapping

Lucie Homolova et al.

ECOLOGICAL COMPLEXITY (2013)

Article Multidisciplinary Sciences

Global Leaf Trait Relationships: Mass, Area, and the Leaf Economics Spectrum

Jeanne L. D. Osnas et al.

SCIENCE (2013)

Article Environmental Sciences

Spatially constrained inversion of radiative transfer models for improved LAI mapping from future Sentinel-2 imagery

Clement Atzberger et al.

REMOTE SENSING OF ENVIRONMENT (2012)

Article Environmental Sciences

LAI assessment of wheat and potato crops by VENμS and Sentinel-2 bands

I. Herrmann et al.

REMOTE SENSING OF ENVIRONMENT (2011)

Article Biodiversity Conservation

Towards an assessment of multiple ecosystem processes and services via functional traits

Francesco de Bello et al.

BIODIVERSITY AND CONSERVATION (2010)

Article Optics

Brightness-normalized Partial Least Squares Regression for hyperspectral data

Hannes Feilhauer et al.

JOURNAL OF QUANTITATIVE SPECTROSCOPY & RADIATIVE TRANSFER (2010)

Review Plant Sciences

Remote sensing of plant functional types

Susan L. Ustin et al.

NEW PHYTOLOGIST (2010)

Review Plant Sciences

Causes and consequences of variation in leaf mass per area (LMA): a meta-analysis

Hendrik Poorter et al.

NEW PHYTOLOGIST (2009)

Article Environmental Sciences

Retrieval of foliar information about plant pigment systems from high resolution spectroscopy

Susan L. Ustin et al.

REMOTE SENSING OF ENVIRONMENT (2009)

Article Environmental Sciences

Characterizing canopy biochemistry from imaging spectroscopy and its application to ecosystem studies

Raymond F. Kokaly et al.

REMOTE SENSING OF ENVIRONMENT (2009)

Article Environmental Sciences

PROSPECT plus SAIL models: A review of use for vegetation characterization

Stephane Jacquemoud et al.

REMOTE SENSING OF ENVIRONMENT (2009)

Article Environmental Sciences

PROSPECT-4 and 5:: Advances in the leaf optical properties model separating photosynthetic pigments

Jean-Baptiste Feret et al.

REMOTE SENSING OF ENVIRONMENT (2008)

Article Environmental Sciences

Spectral and chemical analysis of tropical forests: Scaling from leaf to canopy levels

Gregory P. Asner et al.

REMOTE SENSING OF ENVIRONMENT (2008)

Article Automation & Control Systems

Sparse mzodeling using orthogonal forward regression with PRESS statistic and regularization

S Chen et al.

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS (2004)