Generation Of Satellites Research Articles

InSAR Time Series Analysis of L-Band Wide-Swath SAR Data Acquired by ALOS-2

Operating at L-band (~24 cm wavelength) in wide-swath modes is one of the characteristics of the new and next generation satellite synthetic aperture radar (SAR) missions. After 3 years of operation, the Japan Aerospace Exploration Agency Advanced Land Observing Satellite-2 (ALOS-2) satellite has acquired a wealth of L-band wide-swath SAR data over many areas using its ScanSAR mode. We present interferometry SAR (InSAR) time series analysis results from ALOS-2 ScanSAR data. We analyze the possible error sources in the InSAR and correct them if possible. We present different time series analysis results including azimuth frequency modulation rate error, line of sight (LOS) ionospheric phase, azimuth shift caused by the ionosphere, and LOS displacement processed using both full-aperture and burst-by -burst workflows. The final InSAR LOS displacement time series result reveals both large-scale tectonic and small-scale anthropogenic deformation components. The results demonstrate the potential for measuring continental or even global-scale tectonic deformation and illustrate the promise of upcoming L-band wide-swath SAR missions, such as the NASA-ISRO SAR mission.

Implementation of a new algorithm resulting in improvements in accuracy and resolution of SEVIRI hotspot products

ABSTRACTActive wildfire detection, surveillance and mapping is an important application of satellite remote sensing. The Active Fire Monitoring (FIR) products, from the Spinning Enhanced Visible and Infrared Imager (SEVIRI) on board the Meteosat Second Generation (MSG) satellites, provide rapid-fire detection data every 5 to 15 over the European and African continents. However, the real world application of this high temporal frequency data is hindered due to the product spatial resolution of 3 3, thus limiting the application in fire surveillance and mapping activities. This letter implements a modified version of the Advanced Himawari-8 Imager – Fire Surveillance Algorithm (AHI-FSA) for SEVIRI with the aim of improving the spatial resolution of fire activity mapping. Initial results demonstrate the algorithm was able to improve the resolution of fire detection from 3 3 km to 1 1 km and simultaneously reduce the commission and omission errors by 25% and 16% respectively.

The Global Population of Mesoscale Convective Complexes (MCCs) over Indonesian Maritime Continent during 15 Years

Mesoscale convective complexes (MCCs) were identified and tracked during 15-years over Indonesian Maritime Continent (IMC) by infrared satellite imagery using an algorithm that combines criteria of cloud coverage, eccentricity, and cloud lifetime. Infrared satellite imagery is obtained from the Himawari generation satellite data. This study results that there are several characteristics of MCC over the IMC, among others; Most of these MCCs were over the continental area, mainly near the mountains and the high elevation areas which have similar characteristic with the global population of MCCs in the world. The peak of MCC occurrence over the IMC is during MAM with around 33.56% due to likely linked to the synoptic-scale environment, which is more baroclinic in nature than in the late summer months. Around of 26,26% and 25,29%, MCC occurrences are found in DJF and SON, respectively. The season with fewer events is JJA, around of 14.79%. The average of cloud shield area size of MCCs is around 315,000 km2. The average duration of the MCCs over IMC was approximately ~9.5 hours and the maximum duration was 10 hours. Those observed in this study were usually nocturnal and reached a maximum at midnight.

Evaluating the potential of the red edge channel for C3 (Festuca spp.) grass discrimination using Sentinel-2 and Rapid Eye satellite image data

Integrating the Red Edge channel in satellite sensors is valuable for plant species discrimination. Sentinel-2 MSI and Rapid Eye are some of the new generation satellite sensors that are characterized by finer spatial and spectral resolution, including the red edge band. The aim of this study was to evaluate the potential of the red edge band of Sentinel-2 and Rapid Eye, for mapping festuca C3 grass using discriminant analysis and maximum likelihood classification algorithms. Spectral bands, vegetation indices and spectral bands plus vegetation indices were analysed. Results show that the integration of the red edge band improved the festuca C3 grass mapping accuracy by 5.95 and 4.76% for Sentinel-2 and Rapid Eye when the red edge bands were included and excluded in the analysis, respectively. The results demonstrate that the use of sensors with strategically positioned red edge bands, could offer information that is critical for the sustainable rangeland management.

Mesoscale Convective Complexes (MCCs) over the Indonesian Maritime Continent during the ENSO events

This study analyzed the mesoscale convective complexes (MCCs) over the Indonesian Maritime Continent (IMC) during the El Niño/Southern Oscillation (ENSO) events for the the15-year period from 2001 to 2015. The MCCs identified by infrared satellite imagery that obtained from the Himawari generation satellite data. This study has reported that the frequencies of the MCC occurrences at the El Niño and La Niña were higher than that of neutral conditions during DJF. Peak of MCC occurrences during DJF at La Niña and neutral condition is in February, while El Niño is in January. ENSO strongly affects the occurrence of MCC during the DJF season. The existences of the MCC were also accompanied by increased rainfall intensity at the locations of the MCC occurrences for all ENSO events. During JJA seasons, the MCC occurrences are always found during neutral conditions, El Niño and La Niña in Indian Ocean. MCC occurring during the JJA season on El Niño and neutral conditions averaged much longer than during the DJF season. In contrast, MCCs occurring in La Niña conditions during the JJA season are more rapidly extinct than during the DJF. It indicates that the influence of MCC during La Niña during the DJF season is stronger than during the JJA season.

Characteristics of the oceanic MCC, continental MCC, and coastal MCC over the Indonesian maritime continent

This study explains the comparison of mesoscale convective complexes (MCC) characteristics in the oceans, land and in the coast over Indonesian maritime continent (IMC). MCCs were identified and tracked during 15-years (2001-2015) over IMC by infrared satellite imagery using an algorithm that combines criteria of cloud coverage, eccentricity, and cloud lifetime. Infrared satellite imagery was obtained from Himawari generation satellite data. This study showed most of the continental MCC found near the mountains and the high elevation areas. The frequency of MCC occurrences was larger over the land than over the ocean. The oceanic MCCs, which lasted for more than 12 hours, were longer-lived than the continental MCCs. The MCCs with small size most frequently occurred in the continent, in contrast, the MCC with the medium and large size were most concentrated over the ocean. Generally, the continental and coastal MCC initiation occurs in the late afternoon and reach maximum size around midnight before decaying the next morning. In contrast, the oceanic MCC dominantly develops in midnight, and reach maximum size in the morning and then MCC decayed and dissipated from noon until afternoon. The evolution of MCC development in the ocean, land, and in the coast has almost the same stages and ways.

Estimating Peatland Water Table Depth and Net Ecosystem Exchange: A Comparison between Satellite and Airborne Imagery

Peatlands play a fundamental role in climate regulation through their long-term accumulation of atmospheric carbon. Despite their resilience, peatlands are vulnerable to climate change. Remote sensing offers the opportunity to better understand these ecosystems at large spatial scales through time. In this study, we estimated water table depth from a 6-year time sequence of airborne shortwave infrared (SWIR) hyperspectral imagery. We found that the narrowband index NDWI1240 is a strong predictor of water table position. However, we illustrate the importance of considering peatland anisotropy on SWIR imagery from the summer months when the vascular plants are in full foliage, as not all illumination conditions are suitable for retrieving water table position. We also model net ecosystem exchange (NEE) from 10 years of Landsat TM5 imagery and from 4 years of Landsat OLI 8 imagery. Our results show the transferability of the model between imagery from sensors with similar spectral and radiometric properties such as Landsat 8 and Sentinel-2. NEE modeled from airborne hyperspectral imagery more closely correlated to eddy covariance tower measurements than did models based on satellite images. With fine spectral, spatial and radiometric resolutions, new generation satellite imagery and airborne hyperspectral imagery allow for monitoring the response of peatlands to both allogenic and autogenic factors.

Determining Optimal New Generation Satellite Derived Metrics for Accurate C3 and C4 Grass Species Aboveground Biomass Estimation in South Africa

While satellite data has proved to be a powerful tool in estimating C3 and C4 grass species Aboveground Biomass (AGB), finding an appropriate sensor that can accurately characterize the inherent variations remains a challenge. This limitation has hampered the remote sensing community from continuously and precisely monitoring their productivity. This study assessed the potential of a Sentinel 2 MultiSpectral Instrument, Landsat 8 Operational Land Imager, and WorldView-2 sensors, with improved earth imaging characteristics, in estimating C3 and C4 grasses AGB in the Cathedral Peak, South Africa. Overall, all sensors have shown considerable potential in estimating species AGB; with the use of different combinations of the derived spectral bands and vegetation indices producing better accuracies. However, WorldView-2 derived variables yielded better predictive accuracies (R2 ranging between 0.71 and 0.83; RMSEs between 6.92% and 9.84%), followed by Sentinel 2, with R2 between 0.60 and 0.79; and an RMSE 7.66% and 14.66%. Comparatively, Landsat 8 yielded weaker estimates, with R2 ranging between 0.52 and 0.71 and high RMSEs ranging between 9.07% and 19.88%. In addition, spectral bands located within the red edge (e.g., centered at 0.705 and 0.745 µm for Sentinel 2), SWIR, and NIR, as well as the derived indices, were found to be very important in predicting C3 and C4 AGB from the three sensors. The competence of these bands, especially of the free-available Landsat 8 and Sentinel 2 dataset, was also confirmed from the fusion of the datasets. Most importantly, the three sensors managed to capture and show the spatial variations in AGB for the target C3 and C4 grassland area. This work therefore provides a new horizon and a fundamental step towards C3 and C4 grass productivity monitoring for carbon accounting, forage mapping, and modelling the influence of environmental changes on their productivity.

Improved synchronisation algorithm based on reconstructed correlation function for BOC modulation in satellite navigation and positioning system

With the development of the new generation satellite navigation and positioning systems utilise binary offset carrier (BOC) modulation to improve inter-operability. The main shortcoming of BOC modulation is its ambiguity of searching for a multi-peaked auto-correlation function (ACF). In this study, an improved unambiguous synchronisation algorithm based on compensated correlation reconstructed technique (CCRT) is proposed for the arbitrary-order BOC, which is a new modulation technique for navigation modernisation. The key technique used in this study is to generate local reference signals with different shape vectors. By recombining the piecewise correlation functions of the step-shape coded symbol, a reconstructed correlation function which has only one peak is obtained, and the energy loss is compensated by the ACF. In the proposed algorithm, different shape vectors are employed in different BOC modulation signals. The simulation results demonstrate that the ambiguity problem is completely eliminated. Compared with traditional synchronisation methods, the proposed algorithm shows outstanding detection and multipath mitigation performance. Moreover, the CCRT can be utilised for arbitrary stage BOC modulation signals.

The Role of NWP Filter for the Satellite Based Detection of Cumulonimbus Clouds

This study is motivated by the great importance of Cbs for aviation safety. The study investigates the role of Numerical Weather Prediction (NWP) filtering for the remote sensing of Cumulonimbus Clouds (Cbs) by implementation of about 30 different experiments, covering Central Europe. These experiments compile different stability filter settings as well as the use of different channels for the InfraRed (IR) brightness temperatures (BT). As stability filters, parameters from Numerical Weather Prediction (NWP) are used. The application of the stability filters restricts the detection of Cbs to regions with a labile atmosphere. Various NWP filter settings are investigated in the experiments. The brightness temperature information results from the infrared (IR) Spinning Enhanced Visible and InfraRed Image (SEVIRI) instrument on-board of the Meteosat Second Generation satellite and enables the detection of very cold and high clouds close to the tropopause. Various satellite channels and BT thresholds are applied in the different experiments. The satellite only approaches (no NWP filtering) result in the detection of Cbs with a relative high probability of detection, but unfortunately combined with a large False Alarm Rate (FAR), leading to a Critical Success Index (CSI) below 60% for the investigated summer period in 2016. The false alarms result from other types of very cold and high clouds. It is shown that the false alarms can be significantly decreased by application of an appropriate NWP stability filter, leading to the increase of CSI to about 70% for 2016. CSI is increased from about 70 to about 75% by application of NWP filtering for the other investigated summer period in 2017. A brief review and reflection of the literature clarify that the function of the NWP filter can not be replaced by MSG IR spectroscopy. Thus, NWP filtering is strongly recommended to increase the quality of satellite based Cb detection. Further, it has been shown that the well established convective available potential energy (CAPE) and the convection index (KO) work well as a stability filter.

Development strategies for the satellite flight software on-board Meteosat Third Generation

Nowadays, satellites are becoming increasingly software dependent. Satellite Flight Software (FSW), that is to say, the application software running on the satellite main On-Board Computer (OBC), plays a relevant role in implementing complex space mission requirements. In this paper, we examine relevant technical approaches and programmatic strategies adopted for the development of the Meteosat Third Generation Satellite (MTG) FSW. To begin with, we present its layered model-based architecture, and the means for ensuring a robust and reliable interaction among the FSW components. Then, we focus on the selection of an effective software development life cycle model. In particular, by combining plan-driven and agile approaches, we can fulfill the need of having preliminary SW versions. They can be used for the elicitation of complex system-level requirements as well as for the initial satellite integration and testing activities. Another important aspect can be identified in the testing activities. Indeed, very demanding quality requirements have to be fulfilled in satellite SW applications. This manuscript proposes a test automation framework, which uses an XML-based test procedure language independent of the underlying test environment. Finally, a short overview of the MTG FSW sizing and timing budgets concludes the paper.

Assessment of surface solar irradiance derived from real-time modelling techniques and verification with ground-based measurements

Abstract. This study focuses on the assessment of surface solar radiation (SSR) based on operational neural network (NN) and multi-regression function (MRF) modelling techniques that produce instantaneous (in less than 1 min) outputs. Using real-time cloud and aerosol optical properties inputs from the Spinning Enhanced Visible and Infrared Imager (SEVIRI) on board the Meteosat Second Generation (MSG) satellite and the Copernicus Atmosphere Monitoring Service (CAMS), respectively, these models are capable of calculating SSR in high resolution (1 nm, 0.05∘, 15 min) that can be used for spectrally integrated irradiance maps, databases and various applications related to energy exploitation. The real-time models are validated against ground-based measurements of the Baseline Surface Radiation Network (BSRN) in a temporal range varying from 15 min to monthly means, while a sensitivity analysis of the cloud and aerosol effects on SSR is performed to ensure reliability under different sky and climatological conditions. The simulated outputs, compared to their common training dataset created by the radiative transfer model (RTM) libRadtran, showed median error values in the range −15 to 15 % for the NN that produces spectral irradiances (NNS), 5–6 % underestimation for the integrated NN and close to zero errors for the MRF technique. The verification against BSRN revealed that the real-time calculation uncertainty ranges from −100 to 40 and −20 to 20 W m−2, for the 15 min and monthly mean global horizontal irradiance (GHI) averages, respectively, while the accuracy of the input parameters, in terms of aerosol and cloud optical thickness (AOD and COT), and their impact on GHI, was of the order of 10 % as compared to the ground-based measurements. The proposed system aims to be utilized through studies and real-time applications which are related to solar energy production planning and use.

Remote monitoring of the state of winter wheat during the spring-summer vegetation of 2016 year, by using vegetation indices of Sentinel-2A satellite (case study by foreststeppe area of Ukraine)

The spectral vegetation indices NDVI (842, 665), NDVI (740, 665) and GreenNDVI received from the survey data of new generation satellite Sentinel2A, were analyzed in publication for studying the vegetation of two cultivars of winter wheat, grown up of crops production for the harvest in 2016 year of Grain Alliance Ukraine (Berezan, Kyiv oblast, Ukraine).

Atomic clock performance and combined clock error prediction for the new generation of BeiDou navigation satellites

Atomic clocks are the core equipment aboard navigation satellites, and their performances and predictions directly determine PNT accuracy. In this paper, the on-orbit performances and prediction accuracies of atomic clocks used in new generation navigation satellites are evaluated using two-way time synchronization data. First, using clock error data preprocessed based on combined MAD gross error detection, the method used to evaluate satellite clock performance is studied. The results illustrate that gross error can be eliminated effectively and that the performances of the new generation of satellites are improved in comparison with those of regional satellites. The frequency accuracy has been enhanced from 6.91 × 10−12 to 3.29 × 10−12, and daily stability has been enhanced from 4.036 × 10−14 to 2.339 × 10−14. Second, a weighted combined clock error prediction model was designed that synthesizes polynomial and gray models using the classical weighted method. The results using the combined models show that the prediction accuracies of the new generation satellites are improved by a factor of two when compared with those for regional satellites, and the mean prediction was enhanced was from 0.77 ns to 0.38 ns. Moreover, from the research findings, it was found that prediction accuracy is significantly correlated with daily stability and frequency accuracy and has a micro-correlation with daily drift rate. Finally, in order to study the prediction accuracies of the new generation of satellites, we studied ISL and concluded that it has greatly increased the measured arc of the MEO satellites and can improve re-entry prediction accuracies from 3–4 ns to 1 ns.

Favourable and Unfavourable Scenarii of Radiative Fog Formation Defined by Ground-Based and Satellite Observation Data

An innovative set of six observed predictors of fog formation by radiative cooling is proposed, which describes: 1) one of the main processes of fog formation that is the water uptake by aerosols at surface level; 2) the fog development along the vertical up to 30 meters, as well as the cloud cover; and 3) the temporal evolution of the parameters describing the water uptake by aerosols and the cloud cover. The visibility is used as a signal of atmospheric and surface processes affecting the water uptake by aerosols. The vertical fog development is described by the vertical thermal gradient along a 30-m meteorological mast. The cloud cover is described using a ceilometer for low and middle clouds above the instrument, and satellite data for clouds in a pixel and in a larger 9 × 9-pixel region around the site. The set of predictors can be observed in operational conditions, such as on airport fields. Data acquired at the SIRTA platform (Paris, France) during two autumns and two winters were analysed, and the cloud cover classification derived from the SEVIRI instrument on the METEOSAT Second Generation satellite by the EUMETSAT/NWCSAF program was also utilized. The training data set was acquired in November 2011 while the validation data set extended over 12 months. All situations were discriminated between favourable and unfavourable scenarii of radiative cooling fog formation, with a factor of 10 in probability. 246 moderate visibility events (with visibility between 5 and 10 km) were observed under a clear sky in 12 months at SIRTA. While developed fog formed according to one scenario, thin fog formed according to six scenarii. On the contrary to thin fog, developed fog did not form when cirrus clouds were observed above moderate visibility situations. The fog formation probability varied from 12 to 43%, and even reached 100% for one thin fog. As the training data set was acquired in autumn, the predictor set seems more appropriate to nowcast fog in humid autumn conditions, when the fog formation probability was multiplied by ~2. The predictive set could be enriched by predictors proposed in literature, and tests suggest that relative humidity would improve the fog formation probability in winter. Five predictors identify 65 of the 217 no-fog events counted in 12 months, with ~3 h anticipation time. If visibility decreased below 5 km, 88 additional no-fog events were identified. In this case, the formation probability was 35% for developed fog, and 24–60% for thin fog, but with an anticipation time reduced to ~1.5 h. Only one fog, which represents 3% of the fog events, would be missed with such a predictive scheme.

Determination of the Correlation between the Air Temperature Measured <i>in Situ</i> and Remotely Sensed Data from MODIS and SEVIRI in Congo-Brazzaville

This study compared data from the MODerate-resolution Imaging Spectroradiometer (MODIS) onboard NASA’s Terra satellite and the Spinning Enhanced Visible and Infrared Imager (SEVIRI) on EUMETSAT’s Meterosat Second Generation (MSG) satellite with in situ data obtained from ground observation stations in Congo-Brazzaville. Remote sensing instruments can be used to estimate air temperature, which has an important role in monitoring the effects of climate change. Congo-Brazzaville is located in equatorial forest, which is difficult to access, and has a limited number of ground meteorological stations measuring air temperature. This study used MODIS and MSG data for the period 2009-2014 to assess the performance of land surface temperature data from satellites against in situ data from ground-based stations in Congo-Brazzaville using a linear regression model. This work has allowed us to determine which satellite is best adapted for use in Central Africa.

High-throughput satellite (HTS) with radio and optical frequencies for the next generation satellite communications

High-throughput satellite (HTS) with radio and optical frequencies for the next generation satellite communications

Characterisation of the artificial neural network CiPS for cirrus cloud remote sensing with MSG/SEVIRI

Abstract. Cirrus clouds remain one of the key uncertainties in atmospheric research. To better understand the properties and physical processes of cirrus clouds, accurate large-scale observations from satellites are required. Artificial neural networks (ANNs) have proved to be a useful tool for cirrus cloud remote sensing. Since physics is not modelled explicitly in ANNs, a thorough characterisation of the networks is necessary. In this paper the CiPS (Cirrus Properties from SEVIRI) algorithm is characterised using the space-borne lidar CALIOP. CiPS is composed of a set of ANNs for the cirrus cloud detection, opacity identification and the corresponding cloud top height, ice optical thickness and ice water path retrieval from the imager SEVIRI aboard the geostationary Meteosat Second Generation satellites. First, the retrieval accuracy is characterised with respect to different land surface types. The retrieval works best over water and vegetated surfaces, whereas a surface covered by permanent snow and ice or barren reduces the cirrus detection ability and increases the retrieval errors for the ice optical thickness and ice water path if the cirrus cloud is thin (optical thickness less than approx. 0.3). Second, the retrieval accuracy is characterised with respect to the vertical arrangement of liquid, ice clouds and aerosol layers as derived from CALIOP lidar data. The CiPS retrievals show little interference from liquid water clouds and aerosol layers below an observed cirrus cloud. A liquid water cloud vertically close or adjacent to the cirrus clearly increases the average retrieval errors for the optical thickness and ice water path, respectively, only for thin cirrus clouds with an optical thickness below 0.3 or ice water path below 5.0 g m−2. For the cloud top height retrieval, only aerosol layers affect the retrieval error, with an increased positive bias when the cirrus is at low altitudes. Third, the CiPS retrieval error is characterised with respect to the properties of the investigated cirrus cloud (ice optical thickness and cloud top height). On average CiPS can retrieve the cirrus cloud top height with a relative error around 8 % and no bias and the ice optical thickness with a relative error around 50 % and bias around ±10 % for the most common combinations of cloud top height and ice optical thickness. Similarities with physically based retrieval methods are evident, which implies that even though the retrieval methods differ in the implementation of physics in the model, the retrievals behave similarly due to physical constraints. Finally, we also show that the ANN retrievals have a low sensitivity to radiometric noise in the SEVIRI observations. For optical thickness and ice water path the relative uncertainty due to noise is less than 10 % down to sub-visual cirrus. For the cloud top height retrieval the uncertainty due to noise is around 100 m for all cloud top heights.

Detecting geothermal anomalies and evaluating LST geothermal component by combining thermal remote sensing time series and land surface model data

This paper explores for the first time the possibilities to use two land surface temperature (LST) time series of different origins (geostationary Meteosat Second Generation satellite data and Noah land surface modelling, LSM), to detect geothermal anomalies and extract the geothermal component of LST, the LSTgt. We hypothesize that in geothermal areas the LSM time series will underestimate the LST as compared to the remote sensing data, since the former does not account for the geothermal component in its model.In order to extract LSTgt, two approaches of different nature (physical based and data mining) were developed and tested in an area of about 560×560km2 centered at the Kenyan Rift. Pre-dawn data in the study area during the first 45days of 2012 were analyzed.The results show consistent spatial and temporal LSTgt patterns between the two approaches, and systematic differences of about 2K. A geothermal area map from surface studies was used to assess LSTgt inside and outside the geothermal boundaries. Spatial means were found to be higher inside the geothermal limits, as well as the relative frequency of occurrence of high LSTgt. Results further show that areas with strong topography can result in anomalously high LSTgt values (false positives), which suggests the need for a slope and aspect correction in the inputs to achieve realistic results in those areas. The uncertainty analysis indicates that large uncertainties of the input parameters may limit detection of LSTgt anomalies. To validate the approaches, higher spatial resolution images from the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data over the Olkaria geothermal field were used. An established method to estimate radiant geothermal flux was applied providing values between 9 and 24W/m2 in the geothermal area, which coincides with the LSTgt flux rates obtained with the proposed approaches.The proposed approaches are a first step in estimating LSTgt at large spatial coverage from remote sensing and LSM data series, and provide an innovative framework for future improvements.

Short-term cloudiness forecasting for solar energy purposes in Greece, based on satellite-derived information

A novel method for the short-term (15–240 min) forecasting of cloudiness in Greece is presented by taking into account that this is the main atmospheric factor responsible for the spatial and temporal distribution of surface solar irradiance. Images from the Spinning Enhanced Visible and Infrared Imager onboard the Meteosat Second Generation satellite, for a 3-year time period and with high spatial and temporal resolution (0.05°, 15 min), were processed to retrieve the cloud clearness index (CCI) and used for the training and testing of an artificial neural network (ANN). The estimated and the measured values of CCI are in good agreement and emphasis is given to the spatial distribution of the seasonal errors. The ANN was trained according to pre-classified areas that present similar cloud characteristics and could provide estimations of surface solar irradiance in synergy with models that calculate surface irradiance under clear skies.