Intercomparison of instruments for measuring leaf area index over rice

2015

Leaf area index (LAI) is a key biophysical parameter used to determine foliage cover and crop growth in environmental studies in order to assess crop yield. LAI estimates can be classified as direct or indirect methods. Direct methods are destructive, time consuming, and difficult to apply over large fields. Indirect methods are non-destructive and cost-effective due to its portability, accuracy and repeatability. In this study, we compare indirect LAI estimates acquired from two classical instruments such as LAI-2000 and digital cameras for hemispherical photography, with LAI estimates acquired with a smart app (PocketLAI) installed on a mobile smartphone. In this work it is shown that LAI…

Capability assessment of the SEVIRI/MSG GPP product for the detection of areas affected by water stress

2020

[ES] Se presenta el nuevo producto de producción primaria bruta (GPP) de EUMETSAT derivado a partir de datos del satélite geoestacionario SEVIRI/MSG (MGPP LSA-411) y se evalúa su potencial para detectar zonas afectadas por estrés hídrico (hot spots). El producto GPP se basa en la aproximación de Monteith, que modela la GPP de la vegetación como el producto de la radiación fotosintéticamente activa (PAR) incidente, la fracción de PAR absorbida (fAPAR) y un factor de eficiencia de uso de la radiación (ε). El potencial del producto MGPP para detectar hot spots se evalúa, utilizando un periodo corto de tres años, a escala local y regional, comparando con datos in situ derivados de medidas en to…

Physics-Aware Gaussian Processes for Earth Observation

2017

Earth observation from satellite sensory data pose challenging problems, where machine learning is currently a key player. In recent years, Gaussian Process (GP) regression and other kernel methods have excelled in biophysical parameter estimation tasks from space. GP regression is based on solid Bayesian statistics, and generally yield efficient and accurate parameter estimates. However, GPs are typically used for inverse modeling based on concurrent observations and in situ measurements only. Very often a forward model encoding the well-understood physical relations is available though. In this work, we review three GP models that respect and learn the physics of the underlying processes …

Retrieval of Physical Parameters With Deep Structured Kernel Regression

2022

Retrieval of vegetation height in rice fields using polarimetric SAR interferometry with TanDEM-X data

2017

This work presents for the first time a demonstration with satellite data of polarimetric SAR interferometry (PolInSAR) applied to the retrieval of vegetation height in rice fields. Three series of dual-pol interferometric SAR data acquired with large baselines (2–3 km) by the TanDEM-X system during its science phase (April–September 2015) are exploited. A novel inversion algorithm especially suited for rice fields cultivated in flooded soil is proposed and evaluated. The validation is carried out over three test sites located in geographically different areas: Sevilla (SW Spain), Valencia (E Spain), and Ipsala (W Turkey), in which different rice types are present. Results are obtained duri…

Generation of global vegetation products from EUMETSAT AVHRR/METOP satellites

2020

We describe the methodology applied for the retrieval of global LAI, FAPAR and FVC from Advanced Very High Resolution Radiometer (AVHRR) onboard the Meteorological-Operational (MetOp) polar orbiting satellites also known as EUMETSAT Polar System (EPS). A novel approach has been developed for the joint retrieval of three parameters (LAI, FVC, and FAPAR) instead of training one model per parameter. The method relies on multi-output Gaussian Processes Regression (GPR) trained over PROSAIL EPS simulations. A sensitivity analysis is performed to assess several sources of uncertainties in retrievals and maximize the positive impact of modeling the noise in training simulations. We describe the ma…

Development of an earth observation processing chain for crop bio-physical parameters at local scale

2015

This paper proposes a full Earth observation processing chaing for biophysical parameter estimation at local scales. In particular, we focus on the Leaf Area Index (LAI) as an essential climate variable required for the monitoring and modeling of land surfaces at local scale. The main goal of this study is tied to the use of optical satellite images to retrieve Earth Observation (EO) biophysical parameters able to describe the spatio-temporal changes in agro-ecosystems at local scale. The objective of this work is two-fold: (i) to set up and update the EO products processing chain at high resolution (local) scale; and (ii) derive multitemporal LAI maps at 30 m resolution to be fed into a cr…

Vegetation vulnerability to drought in Spain

2014

[EN] Frequency of climatic extremes like long duration droughts has increased in Spain over the last century.The use of remote sensing observations for monitoring and detecting drought is justified on the basis that vegetation vigor is closely related to moisture condition. We derive satellite estimates of bio-physical variables such as fractional vegetation cover (FVC) from MODIS/EOS and SEVIRI/MSG time series. The study evaluates the strength of temporal relationships between precipitation and vegetation condition at time-lag and cumulative rainfall intervals. From this analysis, it was observed that the climatic disturbances affected both the growing season and the total amount of vegeta…

Development of an Earth observation processing chain for crop biophysical parameters at local and global scale

2017

[ES] Reseña de tesis doctoral defendida el 17 de Julio de 2017. Lugar: Facultat de Física, Universitat de València.

Drought Monitoring In The Mediterranean Basin Using The Seviri/Msg Gpp Product (Mgpp)

2020

Recently, the Satellite Application Facility for Land Surface Analysis (LSA-SAF) has just released a new product that helps to characterize ecosystem processes, the 10-day LSA SAF GPP product from SEVIRI/MSG data (MGPP LSA-411). The GPP product is based on Monteith's concept, which models GPP as the product of the incoming photosynthetically active radiation (PAR), the fractional absorption of that flux $(\mathrm{f}_{APAR})$ and a light-use efficiency factor $(\varepsilon)$. Preliminary results on the use of the MGPP product in the assessment of ecosystem response to drought events are presented in this work for a short period of three years. A few sites located in the Mediterranean basin a…

Deep learning for agricultural land use classification from Sentinel-2

2020

[ES] En el campo de la teledetección se ha producido recientemente un incremento del uso de técnicas de aprendizaje profundo (deep learning). Estos algoritmos se utilizan con éxito principalmente en la estimación de parámetros y en la clasificación de imágenes. Sin embargo, se han realizado pocos esfuerzos encaminados a su comprensión, lo que lleva a ejecutarlos como si fueran “cajas negras”. Este trabajo pretende evaluar el rendimiento y acercarnos al entendimiento de un algoritmo de aprendizaje profundo, basado en una red recurrente bidireccional de memoria corta a largo plazo (2-BiLSTM), a través de un ejemplo de clasificación de usos de suelo agrícola de la Comunidad Valenciana dentro d…

Daily GPP estimates in Mediterranean ecosystems by combining remote sensing and meteorological data

2015

The accurate representation of terrestrial CO2 uptake (GPP) using Monteith's approach requires a frequent and site-specific parameterization of the model inputs. In this work, an optimization of this approach has been carried out by adjusting the inputs (f(APAR), PAR and epsilon) for the study area, peninsular Spain, a typical Mediterranean region. The daily GPP images have been calculated for 2008 and 2011 with a 1-km spatial resolution and validated by comparison with in situ GPP estimates from the eddy covariance data (direct validation) and by inter-comparison with the MODIS GPP product. The direct validation has evidenced an excellent agreement with correlations up to 0.98 in 2008 and …

Quantifying uncertainty in high resolution biophysical variable retrieval with machine learning

2022

The estimation of biophysical variables is at the core of remote sensing science, allowing a close monitoring of crops and forests. Deriving temporally resolved and spatially explicit maps of parameters of interest has been the subject of intense research. However, deriving products from optical sensors is typically hampered by cloud contamination and the trade-off between spatial and temporal resolutions. In this work we rely on the HIghly Scalable Temporal Adaptive Reflectance Fusion Model (HISTARFM) algorithm to generate long gap-free time series of Landsat surface reflectance data by fusing MODIS and Landsat reflectances. An artificial neural network is trained on PROSAIL inversion to p…

Retrieval of daily gross primary production over Europe and Africa from an ensemble of SEVIRI/MSG products

2018

The main goal of this paper is to derive a method for a daily gross primary production (GPP) product over Europe and Africa taking the full advantage of the SEVIRI/MSG satellite products from the European Organization for the Exploitation of Meteorological Satellites (EUMETSAT) sensors delivered from the Satellite Application Facility for Land Surface Analysis (LSA SAF) system. Special attention is paid to model the daily GPP response from an optimized Montheith's light use efficiency model under dry conditions by controlling water shortage limitations from the actual evapotranspiration and the potential evapotranspiration (PET). The PET was parameterized using the mean daily air temperatur…

Machine Learning Methods for Spatial and Temporal Parameter Estimation

2020

Monitoring vegetation with satellite remote sensing is of paramount relevance to understand the status and health of our planet. Accurate and constant monitoring of the biosphere has large societal, economical, and environmental implications, given the increasing demand of biofuels and food by the world population. The current democratization of machine learning, big data, and high processing capabilities allow us to take such endeavor in a decisive manner. This chapter proposes three novel machine learning approaches to exploit spatial, temporal, multi-sensor, and large-scale data characteristics. We show (1) the application of multi-output Gaussian processes for gap-filling time series of…

Evaluation of the LSA-SAF gross primary production product derived from SEVIRI/MSG data (MGPP)

2020

The objective of this study is to describe a completely new 10-day gross primary production (GPP) product (MGPP LSA-411) based on data from the geostationary SEVIRI/MSG satellite within the LSA SAF (Land Surface Analysis SAF) as part of the SAF (Satellite Application Facility) network of EUMETSAT. The methodology relies on the Monteith approach. It considers that GPP is proportional to the absorbed photosynthetically active radiation APAR and the proportionality factor is known as the light use efficiency ε. A parameterization of this factor is proposed as the product of a εmax, corresponding to the canopy functioning under optimal conditions, and a coefficient quantifying the reduction of …

Downstream Services for Rice Crop Monitoring in Europe: From Regional to Local Scale

2017

The ERMES agromonitoring system for rice cultivations integrates EO data at different resolutions, crop models, and user-provided in situ data in a unified system, which drives two operational downstream services for rice monitoring. The first is aimed at providing information concerning the behavior of the current season at regional/rice district scale, while the second is dedicated to provide farmers with field-scale data useful to support more efficient and environmentally friendly crop practices. In this contribution, we describe the main characteristics of the system, in terms of overall architecture, technological solutions adopted, characteristics of the developed products, and funct…

Global Estimation of Biophysical Variables from Google Earth Engine Platform

2018

This paper proposes a processing chain for the derivation of global Leaf Area Index (LAI), Fraction of Absorbed Photosynthetically Active Radiation (FAPAR), Fraction Vegetation Cover (FVC), and Canopy water content (CWC) maps from 15-years of MODIS data exploiting the capabilities of the Google Earth Engine (GEE) cloud platform. The retrieval chain is based on a hybrid method inverting the PROSAIL radiative transfer model (RTM) with Random forests (RF) regression. A major feature of this work is the implementation of a retrieval chain exploiting the GEE capabilities using global and climate data records (CDR) of both MODIS surface reflectance and LAI/FAPAR datasets allowing the global estim…

A Critical Comparison of Remote Sensing Leaf Area Index Estimates over Rice-Cultivated Areas: From Sentinel-2 and Landsat-7/8 to MODIS, GEOV1 and EUM…

2018

Leaf area index (LAI) is a key biophysical variable fundamental in natural vegetation and agricultural land monitoring and modelling studies. This paper is aimed at comparing, validating and discussing different LAI satellite products from operational services and customized solution based on innovative Earth Observation (EO) data such as Landsat-7/8 and Sentinel-2A. The comparison was performed to assess overall quality of LAI estimates for rice, as a fundamental input of different scale (regional to local) operational crop monitoring systems such as the ones developed during the "An Earth obseRvation Model based RicE information Service" (ERMES) project. We adopted a multiscale approach f…

Shared feature representations of LiDAR and optical images: Trading sparsity for semantic discrimination

2015

This paper studies the level of complementary information conveyed by extremely high resolution LiDAR and optical images. We pursue this goal following an indirect approach via unsupervised spatial-spectral feature extraction. We used a recently presented unsupervised convolutional neural network trained to enforce both population and lifetime spar-sity in the feature representation. We derived independent and joint feature representations, and analyzed the sparsity scores and the discriminative power. Interestingly, the obtained results revealed that the RGB+LiDAR representation is no longer sparse, and the derived basis functions merge color and elevation yielding a set of more expressive…

Joint Gaussian processes for inverse modeling

2017

Solving inverse problems is central in geosciences and remote sensing. Very often a mechanistic physical model of the system exists that solves the forward problem. Inverting the implied radiative transfer model (RTM) equations numerically implies, however, challenging and computationally demanding problems. Statistical models tackle the inverse problem and predict the biophysical parameter of interest from radiance data, exploiting either in situ data or simulated data from an RTM. We introduce a novel nonlinear and nonparametric statistical inversion model which incorporates both real observations and RTM-simulated data. The proposed Joint Gaussian Process (JGP) provides a solid framework…

Derivation of global vegetation biophysical parameters from EUMETSAT Polar System

2020

Abstract This paper presents the algorithm developed in LSA-SAF (Satellite Application Facility for Land Surface Analysis) for the derivation of global vegetation parameters from the AVHRR (Advanced Very High Resolution Radiometer) sensor on board MetOp (Meteorological–Operational) satellites forming the EUMETSAT (European Organization for the Exploitation of Meteorological Satellites) Polar System (EPS). The suite of LSA-SAF EPS vegetation products includes the leaf area index (LAI), the fractional vegetation cover (FVC), and the fraction of absorbed photosynthetically active radiation (FAPAR). LAI, FAPAR, and FVC characterize the structure and the functioning of vegetation and are key par…

A global Canopy Water Content product from AVHRR/Metop

2020

Abstract Spatially and temporally explicit canopy water content (CWC) data are important for monitoring vegetation status, and constitute essential information for studying ecosystem-climate interactions. Despite many efforts there is currently no operational CWC product available to users. In the context of the Satellite Application Facility for Land Surface Analysis (LSA-SAF), we have developed an algorithm to produce a global dataset of CWC based on data from the Advanced Very High Resolution Radiometer (AVHRR) sensor on board Meteorological–Operational (MetOp) satellites forming the EUMETSAT Polar System (EPS). CWC reflects the water conditions at the leaf level and information related …

Multitemporal and multiresolution leaf area index retrieval for operational local rice crop monitoring

2016

Abstract This paper presents an operational chain for high-resolution leaf area index (LAI) retrieval from multiresolution satellite data specifically developed for Mediterranean rice areas. The proposed methodology is based on the inversion of the PROSAIL radiative transfer model through the state-of-the-art nonlinear Gaussian process regression (GPR) method. Landsat and SPOT5 data were used for multitemporal LAI retrievals at high-resolution. LAI estimates were validated using time series of in situ LAI measurements collected during the rice season in Spain and Italy. Ground LAI data were collected with smartphones using PocketLAI, a specific phone application for LAI estimation. Temporal…

Multitemporal Monitoring of Plant Area Index in the Valencia Rice District with PocketLAI

2016

Leaf area index (LAI) is a key biophysical parameter used to determine foliage cover and crop growth in environmental studies in order to assess crop yield. Frequently, plant canopy analyzers (LAI-2000) and digital cameras for hemispherical photography (DHP) are used for indirect effective plant area index (PAI(eff)) estimates. Nevertheless, these instruments are expensive and have the disadvantages of low portability and maintenance. Recently, a smartphone app called PocketLAI was presented and tested for acquiring PAI(eff) measurements. It was used during an entire rice season for indirect PAI(eff) estimations and for deriving reference high-resolution PAI(eff) maps. Ground PAI(eff) value…

Understanding deep learning in land use classification based on Sentinel-2 time series

2020

AbstractThe use of deep learning (DL) approaches for the analysis of remote sensing (RS) data is rapidly increasing. DL techniques have provided excellent results in applications ranging from parameter estimation to image classification and anomaly detection. Although the vast majority of studies report precision indicators, there is a lack of studies dealing with the interpretability of the predictions. This shortcoming hampers a wider adoption of DL approaches by a wider users community, as model’s decisions are not accountable. In applications that involve the management of public budgets or policy compliance, a better interpretability of predictions is strictly required. This work aims …

Mapping Leaf Area Index with a Smartphone and Gaussian Processes

2020

Leaf area index (LAI) is a key biophysical parameter used to determine foliage cover and crop growth in environmental studies. Smartphones are nowadays ubiquitous sensor devices with high computational power, moderate cost, and high-quality sensors. A smartphone app, which is called PocketLAI, was recently presented and tested for acquiring ground LAI estimates. In this letter, we explore the use of state-of-the-art nonlinear Gaussian process regression (GPR) to derive spatially explicit LAI estimates over rice using ground data from PocketLAI and Landsat 8 imagery. GPR has gained popularity in recent years because of its solid Bayesian foundations that offer not only high accuracy but also…

A high-resolution, integrated system for rice yield forecasting at district level

2019

Abstract To meet the growing demands from public and private stakeholders for early yield estimates, a high-resolution (2 km × 2 km) rice yield forecasting system based on the integration of the WARM model and remote sensing (RS) technologies was developed. RS was used to identify rice-cropped area and to derive spatially distributed sowing dates, and for the dynamic assimilation of RS-derived leaf area index (LAI) data within the crop model. The system—tested for the main European rice production districts in Italy, Greece, and Spain—performed satisfactorily; >66% of the inter-annual yield variability was explained in six out of eight combinations of ecotype × district, with a maximum of 8…

Patterns Comparison Between Gome-2 Sun-Induced Fluorescence and Msg Gross Primary Production

2018

A comparison between maximum monthly MSG gross primary production (GPP) estimates with the sun-induced chlorophyll fluorescence (SIF) product from the Global Ozone Monitoring Experiment-2 (GOME-2) over Europe and Africa is presented as an indirect validation of MSG GPP estimates. The maximum daily GPP value for each month is derived from daily MSG GPP, which takes full advantage of the SEVIRI/MSG products from the European Organization for the Exploitation of Meteorological Satellites (EUMETSAT) delivered by the Satellite Application Facility for Land Surface Analysis (LSA SAF). A linear relationship found between both products over savanna, grasslands and forests at high latitudes evidence…

Physics-aware Gaussian processes in remote sensing

2018

Abstract Earth observation from satellite sensory data poses challenging problems, where machine learning is currently a key player. In recent years, Gaussian Process (GP) regression has excelled in biophysical parameter estimation tasks from airborne and satellite observations. GP regression is based on solid Bayesian statistics, and generally yields efficient and accurate parameter estimates. However, GPs are typically used for inverse modeling based on concurrent observations and in situ measurements only. Very often a forward model encoding the well-understood physical relations between the state vector and the radiance observations is available though and could be useful to improve pre…

Testing Multi-Sensors Time Series of Lai Estimates to Monitor Rice Phenology: Preliminary Results

2018

Timely and accurate information on crop growth and seasonal dynamics are increasingly needed to develop monitoring systems aimed to detect seasonal anomalies, support site specific management and estimate crop yield at the end of the season. In particular, frequent decametric information nowadays being provided exploiting the new generation of Earth Observation (EO) platforms are fundamental for farm level monitoring. This study presents an analysis aimed at fully exploiting dense time series of EO data derived from the combined use of ESA Sentinel-2A and NASA Landsat-7/8 imageries for crop phenological monitoring. Decametric Leaf Area Index (LAI) maps were generated for the year 2016 by in…

A unified vegetation index for quantifying the terrestrial biosphere

2021

[EN] Empirical vegetation indices derived from spectral reflectance data are widely used in remote sensing of the biosphere, as they represent robust proxies for canopy structure, leaf pigment content, and, subsequently, plant photosynthetic potential. Here, we generalize the broad family of commonly used vegetation indices by exploiting all higher-order relations between the spectral channels involved. This results in a higher sensitivity to vegetation biophysical and physiological parameters. The presented nonlinear generalization of the celebrated normalized difference vegetation index (NDVI) consistently improves accuracy in monitoring key parameters, such as leaf area index, gross prim…

Joint Gaussian Processes for Biophysical Parameter Retrieval

2017

Solving inverse problems is central to geosciences and remote sensing. Radiative transfer models (RTMs) represent mathematically the physical laws which govern the phenomena in remote sensing applications (forward models). The numerical inversion of the RTM equations is a challenging and computationally demanding problem, and for this reason, often the application of a nonlinear statistical regression is preferred. In general, regression models predict the biophysical parameter of interest from the corresponding received radiance. However, this approach does not employ the physical information encoded in the RTMs. An alternative strategy, which attempts to include the physical knowledge, co…

Downscaling rice yield simulation at sub-field scale using remotely sensed LAI data

2019

Abstract Crop modeling and remote sensing are key tools to gain deeper understanding on cropping system dynamics and, ultimately, to increase the sustainability of agricultural productions. This study presents a system to estimate rice yields at sub-field scale based on the integration of a biophysical model and remotely sensed products. Leaf area index (LAI) data derived from decametric optical imageries (i.e., Landsat-8, Landsat-7 and Sentinel–2A) were assimilated into the WARM rice model via automatic recalibration of crop parameters at a fine spatial resolution (30 m × 30 m), targeting the lowest error between simulated and remotely sensed LAI. The performance of the system was evaluate…

Comparison of Canopy Emissivity Parametric Models With TES Emissivity Measurements

2018

Canopy temperature is a key factor in many studies, such as evapotranspiration and heat fluxes estimation. To retrieve it accurately, it is needed a precise characterization of the emissivity in the thermal infrared spectral range. Several parametric models are proposed to retrieved effective emissivity at different observation angles, from the previous knowledge of the vegetation and soil emissivities. The present work compares some of these models with emissivity measurements obtained with Temperature-Emissivity Separation (TES) method. For that, FR97, Mod3 and Rmod3 parametric models have been compared with radiometric measurements. Emissivity measurements were done for 7 different obser…

Latent force models for earth observation time series prediction

2016

We introduce latent force models for Earth observation time series analysis. The model uses Gaussian processes and differential equations to combine data driven modelling with a physical model of the system. The LFM presented here performs multi-output structured regression, adapts to the signal characteristics, it can cope with missing data in the time series, and provides explicit latent functions that allow system analysis and evaluation. We successfully illustrate the performance in challenging scenarios of crop monitoring from space, providing time-resolved time series predictions.

Gap Filling of Biophysical Parameter Time Series with Multi-Output Gaussian Processes

2018

In this work we evaluate multi-output (MO) Gaussian Process (GP) models based on the linear model of coregionalization (LMC) for estimation of biophysical parameter variables under a gap filling setup. In particular, we focus on LAI and fAPAR over rice areas. We show how this problem cannot be solved with standard single-output (SO) GP models, and how the proposed MO-GP models are able to successfully predict these variables even in high missing data regimes, by implicitly performing an across-domain information transfer.

Climate Data Records of Vegetation Variables from Geostationary SEVIRI/MSG Data: Products, Algorithms and Applications

2019

The scientific community requires long-term data records with well-characterized uncertainty and suitable for modeling terrestrial ecosystems and energy cycles at regional and global scales. This paper presents the methodology currently developed in EUMETSAT within its Satellite Application Facility for Land Surface Analysis (LSA SAF) to generate biophysical variables from the Spinning Enhanced Visible and InfraRed Imager (SEVIRI) on board MSG 1-4 (Meteosat 8-11) geostationary satellites. Using this methodology, the LSA SAF generates and disseminates at a time a suite of vegetation products, such as the leaf area index (LAI), the fraction of the photosynthetically active radiation absorbed …

HyperLabelMe : A Web Platform for Benchmarking Remote-Sensing Image Classifiers

2017

HyperLabelMe is a web platform that allows the automatic benchmarking of remote-sensing image classifiers. To demonstrate this platform's attributes, we collected and harmonized a large data set of labeled multispectral and hyperspectral images with different numbers of classes, dimensionality, noise sources, and levels. The registered user can download training data pairs (spectra and land cover/use labels) and submit the predictions for unseen testing spectra. The system then evaluates the accuracy and robustness of the classifier, and it reports different scores as well as a ranked list of the best methods and users. The system is modular, scalable, and ever-growing in data sets and clas…

Traitement de données RGB et Lidar à extrêmement haute résolution: retombées de la compétition de fusion de données 2015 de l'IEEE GRSS - Partie A / …

2016

International audience; In this paper, we discuss the scientific outcomes of the 2015 data fusion contest organized by the Image Analysis and Data Fusion Technical Committee (IADF TC) of the IEEE Geoscience and Remote Sensing Society (IEEE GRSS). As for previous years, the IADF TC organized a data fusion contest aiming at fostering new ideas and solutions for multisource studies. The 2015 edition of the contest proposed a multiresolution and multisensorial challenge involving extremely high-resolution RGB images and a three-dimensional (3-D) LiDAR point cloud. The competition was framed in two parallel tracks, considering 2-D and 3-D products, respectively. In this paper, we discuss the sci…