Natacha Kalecinski - Academia.edu (original) (raw)

Papers by Natacha Kalecinski

EGUGA, Apr 1, 2012

ABSTRACT

AGU Fall Meeting Abstracts, Dec 1, 2019

EGUGA, Apr 1, 2013

ABSTRACT Solar photovoltaic power is a predominant source of electrical power on Reunion Island, ... more ABSTRACT Solar photovoltaic power is a predominant source of electrical power on Reunion Island, regularly providing near 30% of electrical power demand for a few hours per day. However solar power on Reunion Island is strongly modulated by clouds in small temporal and spatial scales. Today regional regulations require that new solar photovoltaic plants be combined with storage systems to reduce electrical power fluctuations on the grid. Hence cloud and solar irradiance forecasting becomes an important tool to help optimize the operation of new solar photovoltaic plants on Reunion Island. Reunion Island, located in the South West of the Indian Ocean, is exposed to persistent trade winds, most of all in winter. In summer, the southward motion of the ITCZ brings atmospheric instabilities on the island and weakens trade winds. This context together with the complex topography of Reunion Island, which is about 60 km wide, with two high summits (3070 and 2512 m) connected by a 1500 m plateau, makes cloudiness very heterogeneous. High cloudiness variability is found between mountain and coastal areas and between the windward, leeward and lateral regions defined with respect to the synoptic wind direction. A detailed study of local dynamics variability is necessary to better understand cloud life cycles around the island. In the presented work, our approach to explore the short-term solar irradiance forecast at local scales is to use the deterministic output from a meso-scale numerical weather prediction (NWP) model, AROME, developed by Meteo France. To start we evaluate the performance of the deterministic forecast from AROME by using meteorological measurements from 21 meteorological ground stations widely spread around the island (and with altitudes from 8 to 2245 m). Ground measurements include solar irradiation, wind speed and direction, relative humidity, air temperature, precipitation and pressure. Secondly we study in the model the local dynamics and thermodynamics that control cloud development and solar irradiance in order to define new predictors to improve probabilistic forecast of solar irradiance.

Atmospheric Measurement Techniques, Mar 4, 2022

Aerosols play a key role in the atmosphere as an important climate forcing in climate assessment ... more Aerosols play a key role in the atmosphere as an important climate forcing in climate assessment (IPCC, 2018, 2019), and their better characterization would improve our knowledge of their properties for a better assessment of their impacts (e.g., Dubovik and King, 2000; Andreae et al., 2002;

In this study we present a model to forecast wheat yield based on the evolution of the Difference... more In this study we present a model to forecast wheat yield based on the evolution of the Difference Vegetation Index (DVI) and the Growing Degree Days (GDD), presented in Franch et al. (2015), but adapted to Franch et al. (2019) model. Additionally, we explore how the Land Surface Temperature (LST) can be included into the model and if this parameter adds any value to the model when combined with the optical information. This study is applied to MODIS data at 1km resolution to monitor the national and state level yield of winter wheat in the United States and Ukraine from 2001 to 2019.

International journal of applied earth observation and geoinformation, Dec 1, 2021

Wheat is the most important commodity traded in the international food market. Thus, accurate and... more Wheat is the most important commodity traded in the international food market. Thus, accurate and timely information on wheat production can help mitigate food price fluctuations. Within the existing operational regional and global scale agricultural monitoring systems that provide information on global crop yield and area forecasts, there are still fundamental gaps: #1. Lack of quantitative Earth Observation (EO) derived crop information, #2. Lack of global but detailed (national or subnational level) and timely crop production forecasts and #3. Lack of information on forecast uncertainties. In this study we present the Agriculture Remotely-sensed Yield Algorithm (ARYA) an EO-based method, advancing the state of EO-data application and usage (addressing gap #1) to forecast wheat yield. The algorithm is based on the evolution of the Difference Vegetation Index (DVI) using MODIS data at 1 km resolution and the Growing Degree Days (GDD) from reanalysis data. Additionally, we explore how Land Surface Temperature (LST) can be included into the model and whether this parameter adds any value to the model performance when combined with the optical information. ARYA is implemented at the national and subnational level to forecast winter wheat yield in the main wheat exporting countries of US,

Remote Sensing, Feb 26, 2021

This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

<p>The Russian forces invaded Ukraine on 24th February 2022 leading  t... more <p>The Russian forces invaded Ukraine on 24th February 2022 leading  to widespread disruption of Ukraine's agricultural system. Ukraine is a major exporter of crops , the invasion therefore poses a significant risk to global food security. Quantifying the extent of this impact is critical, and requires monitoring of Ukraine’s agricultural lands. Total production is one of the prime indicators in this regard. Production in turn is directly proportional to the total harvested area. </p><p> </p><p>Harvested areas at regional scales have previously been estimated from satellite data. The majority of these studies use a complete satellite derived phenological time series and make the assumption that senescence leads to harvest. Both these conditions are not applicable in this case, as harvest estimates are required in-season and all planted fields would not necessarily be harvested due to the conflict . A delayed harvest also results in a long browning phase prior to harvest, making it particularly difficult to differentiate from post-harvest signatures. </p><p> </p><p>Given these constraints and challenges, we developed a method to monitor crop harvest near-real time using high resolution Planet satellite imagery. Our method includes training a model to cluster change patterns on historic data and then identify harvest patterns in the current season. Samples used to train the model consist of information from two consecutive images. Such samples are collected across the season and spatially across four  agro-climatic zones, ensuring we capture a complete representation of change patterns that exist. Clusters are assigned as ‘harvested’ or ‘non-harvested’ by visually inspecting imagery at a higher temporal resolution, using which,  harvest can be seen as a clear change event. On clusters which are not fully separable, we apply a hierarchical approach to further separate them. Our method works in the absence of extensive training labels and does not use predefined thresholds or assumptions. We applied the method across the harvesting period for winter crops in Ukraine. </p><p> </p><p>Contrary to initial reports and expectations we found a higher percentage of harvested fields in Ukraine. In free Ukraine we found 94% of planted winter crops to be harvested and in occupied Ukraine it was 88% as of 19th September 2022. Strong visual patterns of non-harvested crops were observed along the occupation borders in eastern and southern Ukraine. Harvesting trends in the north and south were largely unaffected by the conflict. With no possibility to collect ground samples, we visually interpreted satellite imagery at a higher temporal frequency to generate statistically significant validation data for model accuracy calculation. We obtained an overall accuracy of 85% with an f1-score of 90% for the harvested class and 73% for the non-harvested class. Our assessments and analysis were directed to different organizations and agencies dealing with the Ukraine crisis and led to several key insights and derived interpretations.</p><p>Following NASA EarthObservatory article was published based on this work: https://earthobservatory.nasa.gov/images/150590/larger-wheat-harvest-in-</p><p>ukraine-than-expected  </p><p> </p>

IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium

AGU Fall Meeting Abstracts, Dec 1, 2019

La derniere decennie a vu un developpement important de nouvelles methodes de production d'en... more La derniere decennie a vu un developpement important de nouvelles methodes de production d'energie telles que l'energie solaire ou eolienne. Elles occupent une part croissante dans la production d'electricite sur l'ile de la Reunion. Afin d'ameliorer l'integration de l'energie photovoltaique (PV), il est important de coupler la production a des moyens de stockage pour limiter le caractere intermittent de cette source d'energie. Pour optimiser l'utilisation de differentes sources d'energie couplees a la gestion d'une batterie, il est necessaire d'ameliorer la prevision de production PV. Pour obtenir une prevision, il existe plusieurs outils: la prevision deterministe par un modele numerique de prevision meteorologique a meso-echelle, les images satellites, les donnees meteorologiques sol. Les travaux de cette these se place dans ce contexte de prevision de l'energie solaire face a la forte variabilite de l'ennuagement et donc de...

AGU Fall Meeting Abstracts, Dec 1, 2019

Atmospheric Measurement Techniques, Mar 4, 2022

Aerosols play a key role in the atmosphere as an important climate forcing in climate assessment ... more Aerosols play a key role in the atmosphere as an important climate forcing in climate assessment (IPCC, 2018, 2019), and their better characterization would improve our knowledge of their properties for a better assessment of their impacts (e.g., Dubovik and King, 2000; Andreae et al., 2002;

In this study we present a model to forecast wheat yield based on the evolution of the Difference... more In this study we present a model to forecast wheat yield based on the evolution of the Difference Vegetation Index (DVI) and the Growing Degree Days (GDD), presented in Franch et al. (2015), but adapted to Franch et al. (2019) model. Additionally, we explore how the Land Surface Temperature (LST) can be included into the model and if this parameter adds any value to the model when combined with the optical information. This study is applied to MODIS data at 1km resolution to monitor the national and state level yield of winter wheat in the United States and Ukraine from 2001 to 2019.

International journal of applied earth observation and geoinformation, Dec 1, 2021

Remote Sensing, Feb 26, 2021

<p>The Russian forces invaded Ukraine on 24th February 2022 leading  t... more <p>The Russian forces invaded Ukraine on 24th February 2022 leading  to widespread disruption of Ukraine's agricultural system. Ukraine is a major exporter of crops , the invasion therefore poses a significant risk to global food security. Quantifying the extent of this impact is critical, and requires monitoring of Ukraine’s agricultural lands. Total production is one of the prime indicators in this regard. Production in turn is directly proportional to the total harvested area. </p><p> </p><p>Harvested areas at regional scales have previously been estimated from satellite data. The majority of these studies use a complete satellite derived phenological time series and make the assumption that senescence leads to harvest. Both these conditions are not applicable in this case, as harvest estimates are required in-season and all planted fields would not necessarily be harvested due to the conflict . A delayed harvest also results in a long browning phase prior to harvest, making it particularly difficult to differentiate from post-harvest signatures. </p><p> </p><p>Given these constraints and challenges, we developed a method to monitor crop harvest near-real time using high resolution Planet satellite imagery. Our method includes training a model to cluster change patterns on historic data and then identify harvest patterns in the current season. Samples used to train the model consist of information from two consecutive images. Such samples are collected across the season and spatially across four  agro-climatic zones, ensuring we capture a complete representation of change patterns that exist. Clusters are assigned as ‘harvested’ or ‘non-harvested’ by visually inspecting imagery at a higher temporal resolution, using which,  harvest can be seen as a clear change event. On clusters which are not fully separable, we apply a hierarchical approach to further separate them. Our method works in the absence of extensive training labels and does not use predefined thresholds or assumptions. We applied the method across the harvesting period for winter crops in Ukraine. </p><p> </p><p>Contrary to initial reports and expectations we found a higher percentage of harvested fields in Ukraine. In free Ukraine we found 94% of planted winter crops to be harvested and in occupied Ukraine it was 88% as of 19th September 2022. Strong visual patterns of non-harvested crops were observed along the occupation borders in eastern and southern Ukraine. Harvesting trends in the north and south were largely unaffected by the conflict. With no possibility to collect ground samples, we visually interpreted satellite imagery at a higher temporal frequency to generate statistically significant validation data for model accuracy calculation. We obtained an overall accuracy of 85% with an f1-score of 90% for the harvested class and 73% for the non-harvested class. Our assessments and analysis were directed to different organizations and agencies dealing with the Ukraine crisis and led to several key insights and derived interpretations.</p><p>Following NASA EarthObservatory article was published based on this work: https://earthobservatory.nasa.gov/images/150590/larger-wheat-harvest-in-</p><p>ukraine-than-expected  </p><p> </p>

IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium

AGU Fall Meeting Abstracts, Dec 1, 2019

La derniere decennie a vu un developpement important de nouvelles methodes de production d'en... more La derniere decennie a vu un developpement important de nouvelles methodes de production d'energie telles que l'energie solaire ou eolienne. Elles occupent une part croissante dans la production d'electricite sur l'ile de la Reunion. Afin d'ameliorer l'integration de l'energie photovoltaique (PV), il est important de coupler la production a des moyens de stockage pour limiter le caractere intermittent de cette source d'energie. Pour optimiser l'utilisation de differentes sources d'energie couplees a la gestion d'une batterie, il est necessaire d'ameliorer la prevision de production PV. Pour obtenir une prevision, il existe plusieurs outils: la prevision deterministe par un modele numerique de prevision meteorologique a meso-echelle, les images satellites, les donnees meteorologiques sol. Les travaux de cette these se place dans ce contexte de prevision de l'energie solaire face a la forte variabilite de l'ennuagement et donc de...

EGUGA, Apr 1, 2012

ABSTRACT

AGU Fall Meeting Abstracts, Dec 1, 2019

EGUGA, Apr 1, 2013

ABSTRACT Solar photovoltaic power is a predominant source of electrical power on Reunion Island, ... more ABSTRACT Solar photovoltaic power is a predominant source of electrical power on Reunion Island, regularly providing near 30% of electrical power demand for a few hours per day. However solar power on Reunion Island is strongly modulated by clouds in small temporal and spatial scales. Today regional regulations require that new solar photovoltaic plants be combined with storage systems to reduce electrical power fluctuations on the grid. Hence cloud and solar irradiance forecasting becomes an important tool to help optimize the operation of new solar photovoltaic plants on Reunion Island. Reunion Island, located in the South West of the Indian Ocean, is exposed to persistent trade winds, most of all in winter. In summer, the southward motion of the ITCZ brings atmospheric instabilities on the island and weakens trade winds. This context together with the complex topography of Reunion Island, which is about 60 km wide, with two high summits (3070 and 2512 m) connected by a 1500 m plateau, makes cloudiness very heterogeneous. High cloudiness variability is found between mountain and coastal areas and between the windward, leeward and lateral regions defined with respect to the synoptic wind direction. A detailed study of local dynamics variability is necessary to better understand cloud life cycles around the island. In the presented work, our approach to explore the short-term solar irradiance forecast at local scales is to use the deterministic output from a meso-scale numerical weather prediction (NWP) model, AROME, developed by Meteo France. To start we evaluate the performance of the deterministic forecast from AROME by using meteorological measurements from 21 meteorological ground stations widely spread around the island (and with altitudes from 8 to 2245 m). Ground measurements include solar irradiation, wind speed and direction, relative humidity, air temperature, precipitation and pressure. Secondly we study in the model the local dynamics and thermodynamics that control cloud development and solar irradiance in order to define new predictors to improve probabilistic forecast of solar irradiance.

Atmospheric Measurement Techniques, Mar 4, 2022

Aerosols play a key role in the atmosphere as an important climate forcing in climate assessment ... more Aerosols play a key role in the atmosphere as an important climate forcing in climate assessment (IPCC, 2018, 2019), and their better characterization would improve our knowledge of their properties for a better assessment of their impacts (e.g., Dubovik and King, 2000; Andreae et al., 2002;

In this study we present a model to forecast wheat yield based on the evolution of the Difference... more In this study we present a model to forecast wheat yield based on the evolution of the Difference Vegetation Index (DVI) and the Growing Degree Days (GDD), presented in Franch et al. (2015), but adapted to Franch et al. (2019) model. Additionally, we explore how the Land Surface Temperature (LST) can be included into the model and if this parameter adds any value to the model when combined with the optical information. This study is applied to MODIS data at 1km resolution to monitor the national and state level yield of winter wheat in the United States and Ukraine from 2001 to 2019.

International journal of applied earth observation and geoinformation, Dec 1, 2021

Wheat is the most important commodity traded in the international food market. Thus, accurate and... more Wheat is the most important commodity traded in the international food market. Thus, accurate and timely information on wheat production can help mitigate food price fluctuations. Within the existing operational regional and global scale agricultural monitoring systems that provide information on global crop yield and area forecasts, there are still fundamental gaps: #1. Lack of quantitative Earth Observation (EO) derived crop information, #2. Lack of global but detailed (national or subnational level) and timely crop production forecasts and #3. Lack of information on forecast uncertainties. In this study we present the Agriculture Remotely-sensed Yield Algorithm (ARYA) an EO-based method, advancing the state of EO-data application and usage (addressing gap #1) to forecast wheat yield. The algorithm is based on the evolution of the Difference Vegetation Index (DVI) using MODIS data at 1 km resolution and the Growing Degree Days (GDD) from reanalysis data. Additionally, we explore how Land Surface Temperature (LST) can be included into the model and whether this parameter adds any value to the model performance when combined with the optical information. ARYA is implemented at the national and subnational level to forecast winter wheat yield in the main wheat exporting countries of US,

Remote Sensing, Feb 26, 2021

This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

<p>The Russian forces invaded Ukraine on 24th February 2022 leading  t... more <p>The Russian forces invaded Ukraine on 24th February 2022 leading  to widespread disruption of Ukraine's agricultural system. Ukraine is a major exporter of crops , the invasion therefore poses a significant risk to global food security. Quantifying the extent of this impact is critical, and requires monitoring of Ukraine’s agricultural lands. Total production is one of the prime indicators in this regard. Production in turn is directly proportional to the total harvested area. </p><p> </p><p>Harvested areas at regional scales have previously been estimated from satellite data. The majority of these studies use a complete satellite derived phenological time series and make the assumption that senescence leads to harvest. Both these conditions are not applicable in this case, as harvest estimates are required in-season and all planted fields would not necessarily be harvested due to the conflict . A delayed harvest also results in a long browning phase prior to harvest, making it particularly difficult to differentiate from post-harvest signatures. </p><p> </p><p>Given these constraints and challenges, we developed a method to monitor crop harvest near-real time using high resolution Planet satellite imagery. Our method includes training a model to cluster change patterns on historic data and then identify harvest patterns in the current season. Samples used to train the model consist of information from two consecutive images. Such samples are collected across the season and spatially across four  agro-climatic zones, ensuring we capture a complete representation of change patterns that exist. Clusters are assigned as ‘harvested’ or ‘non-harvested’ by visually inspecting imagery at a higher temporal resolution, using which,  harvest can be seen as a clear change event. On clusters which are not fully separable, we apply a hierarchical approach to further separate them. Our method works in the absence of extensive training labels and does not use predefined thresholds or assumptions. We applied the method across the harvesting period for winter crops in Ukraine. </p><p> </p><p>Contrary to initial reports and expectations we found a higher percentage of harvested fields in Ukraine. In free Ukraine we found 94% of planted winter crops to be harvested and in occupied Ukraine it was 88% as of 19th September 2022. Strong visual patterns of non-harvested crops were observed along the occupation borders in eastern and southern Ukraine. Harvesting trends in the north and south were largely unaffected by the conflict. With no possibility to collect ground samples, we visually interpreted satellite imagery at a higher temporal frequency to generate statistically significant validation data for model accuracy calculation. We obtained an overall accuracy of 85% with an f1-score of 90% for the harvested class and 73% for the non-harvested class. Our assessments and analysis were directed to different organizations and agencies dealing with the Ukraine crisis and led to several key insights and derived interpretations.</p><p>Following NASA EarthObservatory article was published based on this work: https://earthobservatory.nasa.gov/images/150590/larger-wheat-harvest-in-</p><p>ukraine-than-expected  </p><p> </p>

IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium

AGU Fall Meeting Abstracts, Dec 1, 2019

La derniere decennie a vu un developpement important de nouvelles methodes de production d'en... more La derniere decennie a vu un developpement important de nouvelles methodes de production d'energie telles que l'energie solaire ou eolienne. Elles occupent une part croissante dans la production d'electricite sur l'ile de la Reunion. Afin d'ameliorer l'integration de l'energie photovoltaique (PV), il est important de coupler la production a des moyens de stockage pour limiter le caractere intermittent de cette source d'energie. Pour optimiser l'utilisation de differentes sources d'energie couplees a la gestion d'une batterie, il est necessaire d'ameliorer la prevision de production PV. Pour obtenir une prevision, il existe plusieurs outils: la prevision deterministe par un modele numerique de prevision meteorologique a meso-echelle, les images satellites, les donnees meteorologiques sol. Les travaux de cette these se place dans ce contexte de prevision de l'energie solaire face a la forte variabilite de l'ennuagement et donc de...

AGU Fall Meeting Abstracts, Dec 1, 2019

Atmospheric Measurement Techniques, Mar 4, 2022

Aerosols play a key role in the atmosphere as an important climate forcing in climate assessment ... more Aerosols play a key role in the atmosphere as an important climate forcing in climate assessment (IPCC, 2018, 2019), and their better characterization would improve our knowledge of their properties for a better assessment of their impacts (e.g., Dubovik and King, 2000; Andreae et al., 2002;

In this study we present a model to forecast wheat yield based on the evolution of the Difference... more In this study we present a model to forecast wheat yield based on the evolution of the Difference Vegetation Index (DVI) and the Growing Degree Days (GDD), presented in Franch et al. (2015), but adapted to Franch et al. (2019) model. Additionally, we explore how the Land Surface Temperature (LST) can be included into the model and if this parameter adds any value to the model when combined with the optical information. This study is applied to MODIS data at 1km resolution to monitor the national and state level yield of winter wheat in the United States and Ukraine from 2001 to 2019.

International journal of applied earth observation and geoinformation, Dec 1, 2021

Remote Sensing, Feb 26, 2021

<p>The Russian forces invaded Ukraine on 24th February 2022 leading  t... more <p>The Russian forces invaded Ukraine on 24th February 2022 leading  to widespread disruption of Ukraine's agricultural system. Ukraine is a major exporter of crops , the invasion therefore poses a significant risk to global food security. Quantifying the extent of this impact is critical, and requires monitoring of Ukraine’s agricultural lands. Total production is one of the prime indicators in this regard. Production in turn is directly proportional to the total harvested area. </p><p> </p><p>Harvested areas at regional scales have previously been estimated from satellite data. The majority of these studies use a complete satellite derived phenological time series and make the assumption that senescence leads to harvest. Both these conditions are not applicable in this case, as harvest estimates are required in-season and all planted fields would not necessarily be harvested due to the conflict . A delayed harvest also results in a long browning phase prior to harvest, making it particularly difficult to differentiate from post-harvest signatures. </p><p> </p><p>Given these constraints and challenges, we developed a method to monitor crop harvest near-real time using high resolution Planet satellite imagery. Our method includes training a model to cluster change patterns on historic data and then identify harvest patterns in the current season. Samples used to train the model consist of information from two consecutive images. Such samples are collected across the season and spatially across four  agro-climatic zones, ensuring we capture a complete representation of change patterns that exist. Clusters are assigned as ‘harvested’ or ‘non-harvested’ by visually inspecting imagery at a higher temporal resolution, using which,  harvest can be seen as a clear change event. On clusters which are not fully separable, we apply a hierarchical approach to further separate them. Our method works in the absence of extensive training labels and does not use predefined thresholds or assumptions. We applied the method across the harvesting period for winter crops in Ukraine. </p><p> </p><p>Contrary to initial reports and expectations we found a higher percentage of harvested fields in Ukraine. In free Ukraine we found 94% of planted winter crops to be harvested and in occupied Ukraine it was 88% as of 19th September 2022. Strong visual patterns of non-harvested crops were observed along the occupation borders in eastern and southern Ukraine. Harvesting trends in the north and south were largely unaffected by the conflict. With no possibility to collect ground samples, we visually interpreted satellite imagery at a higher temporal frequency to generate statistically significant validation data for model accuracy calculation. We obtained an overall accuracy of 85% with an f1-score of 90% for the harvested class and 73% for the non-harvested class. Our assessments and analysis were directed to different organizations and agencies dealing with the Ukraine crisis and led to several key insights and derived interpretations.</p><p>Following NASA EarthObservatory article was published based on this work: https://earthobservatory.nasa.gov/images/150590/larger-wheat-harvest-in-</p><p>ukraine-than-expected  </p><p> </p>

IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium

AGU Fall Meeting Abstracts, Dec 1, 2019

La derniere decennie a vu un developpement important de nouvelles methodes de production d'en... more La derniere decennie a vu un developpement important de nouvelles methodes de production d'energie telles que l'energie solaire ou eolienne. Elles occupent une part croissante dans la production d'electricite sur l'ile de la Reunion. Afin d'ameliorer l'integration de l'energie photovoltaique (PV), il est important de coupler la production a des moyens de stockage pour limiter le caractere intermittent de cette source d'energie. Pour optimiser l'utilisation de differentes sources d'energie couplees a la gestion d'une batterie, il est necessaire d'ameliorer la prevision de production PV. Pour obtenir une prevision, il existe plusieurs outils: la prevision deterministe par un modele numerique de prevision meteorologique a meso-echelle, les images satellites, les donnees meteorologiques sol. Les travaux de cette these se place dans ce contexte de prevision de l'energie solaire face a la forte variabilite de l'ennuagement et donc de...