Estimation of monthly air-sea CO2 flux in the southern Atlantic and Indian Ocean using in-situ and remotely sensed data

Empirical relationships between the sea surface partial pressure of carbon dioxide (pCO₂), sea surface chlorophyll-a concentration (Chl-a), and sea surface temperature (SST), were derived from shipboard pCO₂ measurements in sea water and atmosphere, in-situ Chl-a, and SST data along cruise tracks between Zhongshan Station in East Antarctica and Changcheng Station on the Antarctic Peninsula in December 1999, January 2000, December 2004 and January 2005 during the CHINARE XVI and XXI campaigns. These relationships were then applied to datasets of remotely sensed Chl-a and SST to estimate the monthly air-sea carbon flux and the uptake of atmospheric CO₂ in the southern Atlantic and Indian Ocean. The results show significant spatial and temporal variability of carbon flux in the southern Atlantic and Indian Ocean. The monthly uptakes of atmospheric CO₂ in the region from 50°S to the ice edge between 60°W and 80°E are − 0.00355 GtC, − 0.00573 GtC in December 1999 and January 2000, and − 0.00361 GtC, − 0.00525 GtC in December 2004 and January 2005, respectively.     

Application of satellite remote sensing techniques for estimating air–sea CO2 fluxes in Hudson Bay,Canada during the ice-free season

The role of coastal seas as either a sink or a source of CO₂ is subject to a great deal of uncertainty. This uncertainty largely arises from a lack of observations in the coastal zones. Remote sensing offers an avenue for expanding these observations by allowing for the extrapolation of relatively limited data sets of dissolved CO₂ (pCO_2sw). In this paper, predictive algorithms for pCO_2sw that could be applied to remote sensing products were created from a field data set collected from September–October, 2005 in Hudson Bay, Canada. The field data showed that an effective pCO_2sw interpolation algorithm could be created using sea surface temperature (SST) as a predictor, and that a slight improvement of the algorithm could be achieved if measurements of absorption due to coloured dissolved organic material (a_CDOM) were included. Unfortunately, satellite retrievals of a_CDOM did not match well with in situ observations, and so only SST (obtained from the MODIS Aqua sensor) was used to create monthly maps of pCO_2sw for the period of August–October. To estimate fluxes of CO₂, constructed surfaces of pCO_2sw were combined with estimates of gas transfer velocity derived from QuikSCAT wind retrievals, and pCO_2air based on field observations. The results of these calculations revealed that Hudson Bay acts as a source of CO₂ during August and September, but reverts to a sink of CO₂ in October as the water temperature decreases. Overall, a positive flux of 1.60 TgC was estimated for the region during the ice-free season. This result is in contrast to most Arctic or sub-Arctic continental shelf seas, where usually strong absorptions of CO₂ are observed.     

Estimates of sea surface nitrate concentrations from sea surface temperature and chlorophyll concentration in upwelling areas: A case study for the Benguela system

The knowledge of nitrate fields at global or regional scales in the ocean is fundamental for the study of oceanic biogeochemical processes, particularly those linked to new primary production. The estimate of nitrate concentrations from space is generally based on empirical inverse relationships between sea surface temperature (SST) and nitrate concentrations. These relationships, however, are often highly variable spatially and temporally, and hardly applicable to large areas (i.e., larger than a few degrees in latitude). In this paper we propose a new approach specifically developed for areas influenced by upwelling processes. It relates the nitrate concentration to the difference between SST and the estimated temperature of the upwelled water (variable with latitude and season), δT, which is an indicator of the time elapsed since upwelling. This approach is tested for the Benguela upwelling system, and algorithms are developed using in situ data provided by the World Ocean Database 2005 of the NOAA-NESDIS-National Oceanographic Data Center. The results reveal a significant improvement compared to the NO₃-SST relationships, and a single algorithm can be applied to the whole upwelling area (15 to 35°S). Further improvement is gained by coupling this approach with a method that derives sea surface nitrate concentrations from SST and surface chlorophyll a concentration using multiple regression analyses, as proposed by Goes et al. [Goes, Saino, Oaku, Jiang, (1999). Method for estimating sea surface nitrate concentrations from remotely sensed SST and chlorophyll a: A case study for the North Pacific Ocean using OCTS/ADEOS data. IEEE Transactions on Geoscience and Remote Sensing, 37, no. 3 II, 1633-1644].     

Crop yield prediction from remotely sensed vegetation indices and primary productivity in arid and semi-arid lands

Global demands for biomass and arable lands are expected to double in the next 35 years. Scarcity of water resources in arid and semi-arid areas poses a serious threat to their agricultural productivity and hence their food security. In this study, we examine whether crop yields can be predicted from remotely sensed vegetation indices and remotely sensed estimates of primary productivity. Spatial relationships between remotely sensed enhanced vegetation index (EVI), net photosynthesis (P_Net), and gross and net primary production (GPP and NPP, respectively) in irrigated semi-arid and arid agro-ecosystems since the beginning of the century are analysed. The conflict-affected country of Syria is selected as the case study. Relationships between EVI and crop yield are investigated in an effort to enhance food production estimates in affected areas outside governmental jurisdictions. Estimates of NPP derived from reported irrigated agriculture crop data in a semi-arid and an arid zone are compared to remotely sensed NPP in a geospatial environment. Results show that winter crop yields are correlated with spring GPP in semi-arid zones of the study area (R² = 0.85). Summer crop yield can be predicted from either cumulative summer EVI (R² = 0.77) or P_Net in most zones. Where fully irrigated fields are surrounded by hyper-arid landscape, summer P_Net was negative in all instances and EVI was inversely correlated with yield. NPP from crops was much higher (290 gC m^?2 year^?1) in those regions than MOD17 NPP (70 gC m^–2), where 1.0 g of carbon is equivalent to 2.2 g of oven-dry organic matter (= 45% carbon by weight). The gap was less in semi-arid zones (2–39% difference). Overall crop-derived NPP for the period 2000–2013 was 322 versus 300 gC m^–2 for that remotely sensed within the cropped zones of the political units. The results of this study are crucial to derive accurate estimates of irrigated agriculture productivity and to study the effect of the latter on net ecosystem carbon storage.     

Direct and Indirect Estimation of Leaf Area Index,fAPAR, and Net Primary Production of Terrestrial Ecosystems

A primary objective of the Earth Observing System (EOS) is to develop and validate algorithms to estimate leaf area index (L), fraction of absorbed photosynthetically active radiation (f_APAR), and net primary production (NPP) from remotely sensed products. These three products are important because they relate to or are components of the metabolism of the biosphere and can be determined for terrestrial ecosystems from satellite-borne sensors. The importance of these products in the EOS program necessitates the need to use standard methods to obtain accurate ground truth estimates of L, f_APAR, and NPP that are correlated to satellite-derived estimates. The objective of this article is to review direct and indirect methods used to estimate L, f_APAR, and NPP in terrestrial ecosystems. Direct estimates of L, biomass, and NPP can be obtained by harvesting individual plants, developing allometric equations, and applying these equations to all individuals in the stand. Using non-site-specific allometric equations to estimate L and foliage production can cause large errors because carbon allocation to foliage is influenced by numerous environmental and ecological factors. All of the optical instruments that indirectly estimate L actually estimate “effective” leaf area index (L_E) and underestimate L when foliage in the canopy is nonrandomly distributed (i.e., clumped). We discuss several methods, ranging from simple to complex in terms of data needs, that can be used to correct estimates of L when foliage is clumped. Direct estimates of above-ground and below-ground net primary production (NPP_A and NPP_B, respectively) are laborious, expensive and can only be carried out for small plots, yet there is a great need to obtain global estimates of NPP. Process models, driven by remotely sensed input parameters, are useful tools to examine the influence of global change on the metabolism of terrestrial ecosystems, but an incomplete understanding of carbon allocation continues to hamper development of more accurate NPP models. We summarize carbon allocation patterns for major terrestrial biomes and discuss emerging allocation patterns that can be incorporated into global NPP models. One common process model, light use efficiency or epsilon model, uses remotely sensed f_APAR, light use efficiency (LUE) and carbon allocation coefficients, and other meteorological data to estimates NPP. Such models require reliable estimates of LUE. We summarize the literature and provide LUE coefficients for the major biomes, being careful to correct for inconsistencies in radiation, dry matter and carbon allocation units.     

Diurnal variations in AVHRR SST fields: A strategy for removing warm layer effects from daily images

Different methodologies to estimate the amplitude of the sea surface temperature diurnal variation (DV) and remove it from remotely sensed SST images have been proposed in the last years. Among these, the parameterization proposed by [Stuart-Menteth et al., 2004a] and [Stuart-Menteth et al., 2004b] [Stuart-Menteth, A.C., Robinson, I.S., & Weller, R.A. (2004a). Sensitivity of the diurnal warm layer to meteorological fluctuations Part 1: observations, submitted to Journal of Atmospheric and Ocean Science; Stuart-Menteth, A.C., Robinson, I. S., & Donlon, C.J. (2004b). Sensitivity of the diurnal warm layer to meteorological fluctuations Part 2: a new parameterisation for diurnal warming, submitted to Journal of Atmospheric and Ocean Science] and adopted by the GHRSST-PP (Donlon, 2004) [Donlon, C.J., ad the GHRSST-PP Science Team, 2004: The GHRSST-PP data processing specification v1.0 (GDS v1.0, revision 1.5), GHRSST-PP Report N. 17, Published by the International GHRSST-PP Project Office, pp. 241] appeared as the most promising. In fact, it takes into account wind and insolation variations during the day, that effectively drive the SST diurnal cycle.This parameterization has been tested on 6 months of NOAA-16 AVHRR images acquired and processed at CNR with Pathfinder algorithm. The tests evidenced some limits for a correct estimation of the DV in low-wind regimes for any insolation condition, and in high insolation regimes (>600 W/m²) when the wind intensity increases or decreases of more than 2 m/s during the morning. The limits of applicability of the DV correction to NOAA-16 AVHRR data (at least for the Mediterranean area) were thus identified, and data outside these limits were flagged. However, some anomalous heating were not corrected even with these constraints, due to the lack of accuracy in the wind field used for the correction. As a result, a strategy to flag residual outliers in the corrected daily images has been developed, based on the comparison to an optimally interpolated night SST field of the previous day.     

Estimating phytoplankton biomass in coastal waters of Alaska using airborne remote sensing

Empirical airborne remote-sensing relationships were examined to estimate chlorophyll a concentration in the first optical depth (chl_FOD) of coastal waters of Afgonak/Kodiak Islands during July-August 2002. Band-ratio and spectral-curvature models were tested using satellite remote-sensing reflectance (R_rs(λ)) measurements. Additional shipboard and airborne R_rs(λ) data were also analysed to evaluate consistency of proposed chl_FOD-R_rs(λ) relationships. Validation of chlorophyll algorithms was performed using data collected in the northern-part of the Gulf of Alaska and Bering Sea during 1996, 2002, and 2003 cruises. Likewise, oceanographic conditions during the surveys were typified to interpret variability of chl_FOD fields. The SeaWiFS band-ratio algorithm OC2d was the most sensitive R_rs combination (R_rs(509)/R_rs(553)) to detect chl_FOD variability. Conversely, OC2a (R_rs(412)/R_rs(553)) had the lowest performance to derive chl_FOD values. No valid statistical regressions were established for spectral-curvature relationships in the blue spectrum (< 500 nm). Fertile waters (> 5 mg m^− 3) were preferentially located over shallow banks (∼50 m) and at the entrance of the bays. The approach used in this study to derive chl_FOD values could be universal for Alaskan coastal waters. However, chl_FOD-R_rs(λ) relationships must be calibrated locally for a given season.     

Dynamic change of CO2 flux over bare soil field and its relationship with remotely sensed surface temperature

This study investigated the potential of thermal remote sensing for estimating ecosystem surface CO₂ flux. Ecosystem surface CO₂ flux was measured by an eddy covariance method for more than 3 years, in conjunction with thermal and optical remote sensing measurements as well as micrometeorological, soil and plant measurements. The soil was Andisol (Hydric Hapludands), a humic volcanic ash soil, which is the major cultivated soil for upland crops in Japan. The soil surface CO₂ flux under bare soil conditions was best correlated with the remotely sensed surface temperature, while air temperature was less well correlated and soil temperature and soil water content were poorly correlated. The relationship was well expressed by an exponential Q ₁₀ function (r ²=0.66, RMSE=0.098). The value of Q ₁₀ and the threshold temperature at which the CO₂ flux approached zero were estimated to be 1.47 and 10.0°C, respectively. Results suggested that the soil surface temperature had the dominant effect on the microbial respiration as well as on the physical processes determining the CO₂ gas transfer at the soil–atmosphere interface. Remotely sensed surface temperature will provide useful information for investigation of CO₂ transfer processes near the soil surface, as well as for quantitative assessment of ecosystem surface CO₂ flux.     

The use of time-integrated NOAA NDVI data and rainfall to assess landscape degradation in the arid shrubland of Western Australia

Ground-based data on total phytomass were collected in 1998 and 1999 from four sampling domains, each nearly 1000 km², within the arid shrubland of Western Australia. These data were used in models relating rainfall and landscape characteristics to total phytomass to provide landscape-scale estimates of total phytomass and rainfall-use efficiency for 1992-1999 (referred to as RUE_P). These modelled estimates were compared with remotely sensed estimates of total phytomass (I-NDVI) and rainfall-use efficiency (I-NDVI/annual rainfall; referred to as RUE_N) using data from NOAA satellites.There was good agreement between ground-based and remotely sensed estimates of total phytomass but less agreement between estimates of rainfall-use efficiency. Partitioning the landscape on the basis of landscape resilience did not improve the amount of variance accounted for in RUE_P or RUE_N and there were conflicting relationships between landscape-scale indicators of landscape function and RUE_N. There was, however, evidence to suggest that temporal change in RUE_N may provide a useful broad-scale indicator of landscape degradation or recovery over decadal time intervals. Recommendations are made for broad-scale application of this indicator based on temporal trends in RUE_N.     

Remote sensing used to detect moisture status of pecan orchards grown in a desert environment

Remote-sensing techniques can detect and up-scale leaf-level physiological responses to large areas, and provide significant and reliable information on water use and irrigation management. The objectives of this study were to screen leaf-level physiological changes that occur during the cyclic irrigation of pecan orchards to determine which responses best represent changes in moisture status of plants and link plant physiological changes to remotely sensed surface reflectance data derived from the Landsat Thematic Mapper and Enhanced Thematic Mapper Plus (ETM+). The study was conducted simultaneously on two southern New Mexico mature pecan orchards. For both orchards, plant physiological responses and remotely sensed surface reflectance data were collected from trees that were either well watered or in water deficit. Remotely sensed variables included reflectance in band 1, the ratio between shortwave infrared (SWIR) bands (B5:B7), the normalized difference vegetation index, and SWIR moisture indices. Midday stem water potential (Ψ_smd) was the best performing leaf-level physiological response variable for detecting moisture status in pecans. The B5:B7 ratio positively and significantly correlated with Ψ_smd in five of six irrigation cycles while multiple linear regression weighted with six remotely sensed surface reflectance variables revealed a significant relationship with moisture status in all cycles in both orchards (R² > 0.73). Because changes in the B5:B7 band ratio and multiple regression of spectral variables correlate with the moisture status of pecan orchards, we conclude that remotely sensed data hold promise for detecting the moisture status of pecans.     

A four-band semi-analytical model for estimating chlorophyll a in highly turbid lakes: The case of Taihu Lake, China

Accurate estimation of phytoplankton chlorophyll a (Chla) concentration from remotely sensed data is particularly challenging in turbid, productive waters. The objectives of this study are to validate the applicability of a semi-analytical three-band algorithm in estimating Chla concentration in the highly turbid, widely variable waters of Taihu Lake, China, and to improve the algorithm using a proposed four-band algorithm. The improved algorithm is expressed as [Rrs(λ₁)^− 1 − Rrs(λ₂)^− 1][Rrs(λ₄)^− 1 − Rrs(λ₃)^− 1]^− 1. The two semi-analytical algorithms are calibrated and evaluated against two independent datasets collected from 2007 and 2005 in Taihu Lake. Strong linear relationships were established between measured Chla concentration and that derived from the three-band algorithm of [Rrs^− 1(660) − Rrs^− 1(692)]Rrs(740) and the four-band algorithm of [Rrs^− 1(662) − Rrs^− 1(693)][Rrs^− 1(740) − Rrs^− 1(705)]^− 1. The first algorithm accounts for 87% and 80% variation in Chla concentration in the 2007 and 2005 datasets, respectively. The second algorithm accounts for 97% of variability in Chla concentration for the 2007 dataset and 87% of variation in the 2005 dataset. The three-band algorithm has a mean relative error (MRE) of 43.9% and 34.7% for the 2007 and 2005 datasets. The corresponding figures for the four-band algorithm are 26.7% and 28.4%. This study demonstrates the potential of the four-band model in estimating Chla even in highly turbid case 2 waters.     

Comparing the utility of microwave and thermal remote-sensing constraints in two-source energy balance modeling over an agricultural landscape

A two-source (soil + vegetation) energy balance model using microwave-derived near-surface soil moisture as a key boundary condition (TSM_SM) and another scheme using thermal-infrared (radiometric) surface temperature (TSM_TH) were applied to remote sensing data collected over a corn and soybean production region in central Iowa during the Soil Moisture Atmosphere Coupling Experiment (SMACEX)/Soil Moisture Experiment of 2002 (SMEX02). The TSM_SM was run using fields of near-surface soil moisture from microwave imagery collected by aircraft on six days during the experiment, yielding a root mean square difference (RMSD) between model estimates and tower measurements of net radiation (Rn) and soil heat flux (G) of approximately 20 W m^− 2, and 45 W m^− 2 for sensible (H) and latent heating (LE). Similar results for H and LE were obtained at landscape/regional scales when comparing model output with transect-average aircraft flux measurements. Flux predictions from the TSM_SM and TSM_TH models were compared for two days when both airborne microwave-derived soil moisture and radiometric surface temperature (T_R) data from Landsat were available. These two days represented contrasting conditions of moderate crop cover/dry soil surface and dense crop cover/moist soil surface. Surface temperature diagnosed by the TSM_SM was also compared directly to the remotely sensed T_R fields as an additional means of model validation. The TSM_SM performed well under moderate crop cover/dry soil surface conditions, but yielded larger discrepancies with observed heat fluxes and T_R under the high crop cover/moist soil surface conditions. Flux predictions from the thermal-based two-source model typically showed biases of opposite sign, suggesting that an average of the flux output from both modeling schemes may improve overall accuracy in flux predictions, in effect incorporating multiple remote-sensing constraints on canopy and soil fluxes.     

Lava flow thermal analysis using three infrared bands of remote-sensing imagery: A study case from Mount Etna 2001 eruption

Infrared remotely sensed data can be used to estimate heat flux and thermal features of active volcanoes. The model proposed by Crisp and Baloga [Crisp, J., Baloga, S., 1990. A model for lava flows with two thermal components, Journal of Geophysical Research, 95, 1255-1270.] for active lava flows considers the thermal flux a function of the fractional area of two thermally distinct radiant surfaces. The larger surface area corresponds to the cooler crust of the flow, the smaller one to fractures in the crust. In this model, the crust temperature T_c, the temperature of the cracks T_h, and the fractional area of the hottest component f_h represent the three unknowns to work out. The simultaneous solution of the Planck equation (“dual-band” technique) for two distinct shortwave infrared (SWIR) bands allows to estimate any two of the parameters T_c, T_h, f_h, if the third is assumed [Dozier, J., 1981. A method for satellite identification of surface temperature fields of subpixel resolution. Remote Sensing Environment, 11, 221-229.]The airborne sensor MIVIS was flown on Mount Etna during the July-August 2001 eruption. This hyperspectral imaging spectrometer offers 72 bands in the SWIR range and 10 bands in thermal infrared (TIR) region of the spectrum, which can be used to solve the dual-band system without any assumptions. Therefore, we can combine three spectral MIVIS bands to obtain simultaneous solutions for the three unknowns. Here, the procedure for solving such a system is presented. It is then demonstrated that a TIR channel is required to better pinpoint solutions to the 2-components model.Finally, the spatial and statistical characteristic of the resultant MIVIS-derived temperature and flux distributions are introduced and statistics for each hot spot investigated.     

A GIS framework for surface-layer soil moisture estimation combining satellite radar measurements and land surface modeling with soil physical property estimation

A GIS framework, the Army Remote Moisture System (ARMS), has been developed to link the Land Information System (LIS), a high performance land surface modeling and data assimilation system, with remotely sensed measurements of soil moisture to provide a high resolution estimation of soil moisture in the near surface. ARMS uses available soil (soil texture, porosity, K_sat), land cover (vegetation type, LAI, Fraction of Greenness), and atmospheric data (Albedo) in standardized vector and raster GIS data formats at multiple scales, in addition to climatological forcing data and precipitation. PEST (Parameter EStimation Tool) was integrated into the process to optimize soil porosity and saturated hydraulic conductivity (K_sat), using the remotely sensed measurements, in order to provide a more accurate estimate of the soil moisture. The modeling process is controlled by the user through a graphical interface developed as part of the ArcMap component of ESRI ArcGIS.     

Basin-scale extrapolation of shipboard pCO2 data by using satellite SST and Chla

A new method for the estimation of basin-scale distribution of pressure of carbon dioxide on the sea surface (pCO₂) by satellite-derived sea surface temperature (SST) and chlorophyll-a concentration (Chla) is presented. 28?557 shipboard pCO₂ data were regressed by second-order multiple regression equations of SST and Chla with a regression error of ±14?µatm and ±17?µatm in the subtropical and subarctic domain, respectively. The monthly-average SST and monthly-maximum Chla (Chlmax) field determined from the Advanced Earth Observing Satellite/Ocean Color Temperature Scanner (ADEOS/OCTS) level 3 Daily Binned Map data were substituted into the multi-regression equation to generate the ‘monthly-typical’ basin-scale pCO₂ field in the North Pacific, and the results agreed well with the climatological field of shipboard pCO₂ observations with an error bar of ±21?µatm except in the case of springtime subarctic North Pacific. The satellite-pCO₂ field also satisfactorily reproduced the principle distribution of pCO₂ in the springtime subarctic North Pacific such as the location of each low-pCO₂ patch observed by the shipboard measurements. The extent of pCO₂ depletion in each pCO₂ patch, however, was not well approximated by the satellite-pCO₂ field. This was caused by the underestimation of Chlmax in these low-pCO₂ patches due to the low frequency of satellite-Chla observations in the springtime subarctic North Pacific due to the cloudiness.     

A first attempt at assimilating microwave-derived SST to improve the predictive capability of a coupled,high-resolution Eta-POM forecasting system

This study implements the assimilation of sea surface temperature (SST) data acquired by passive microwave remote sensing to a high-resolution, primitive-equation ocean model. The aim was to improve a forecasting tool capable of predicting the surface ocean processes linked to the air–sea interactions at sub-mesoscale level using one-way coupled, atmosphere–ocean modelling. An assimilation scheme based on a Newtonian relaxation scheme was fine-tuned to improve the forecasting skill of the ocean model. The ocean model was driven by predicted, synchronous air–sea fluxes derived by an overlying atmosphere model, remotely sensed SST and lateral boundary conditions derived from its previous run. The estimation of the model forecasting error was based on statistical and spatial comparison with remotely sensed observations. The optimal nudging coefficient was found to be 5 × 10^?4 for 12 hours, giving a mean bias of ?0.07°C. Forecast validation was done against calibrated AVHRR scenes using a new approach to calibrate region-specific scenes based on the split-window technique. This work demonstrates the benefit of using passive microwave remote sensing to improve high-resolution ocean forecasting systems. It also shows the high complementarity of infrared and passive microwave satellite sensors to provide information on the surface thermodynamics of the Ionian Sea.     

Clean seas: a North Sea test site

The Clean Seas project focused on the role that existing Earth observing satellites might play in monitoring marine pollution. Results are presented here from August 1997, for the North Sea test site, using sea surface temperature (SST), colour and synthetic aperture radar (SAR) images in conjunction with a hydrodynamic model. There was good correlation between data sources, e.g. between SST and ERS-2 SAR images. Both datasets showed the development of fine plume structures close to the Rhine outflow, apparently associated with the outflow, and possibly caused by tidal pulsing of the Rhine Plume.

The model reproduced general temperature and sediment distributions well, but fine structures were not reproduced. Model sediment distribution patterns were verified using ‘chlorophyll concentration’ data from colour sensors, representative of sediment concentration in turbid water. In conjunction with the visible channels of the Advanced Very High Resolution Radiometer and Along-Track Scanning Radiometer, they give an uncalibrated measure of the sediment load. The model gives a more complete picture of the temporal dispersion of the Rhine Plume over time than is evident from the remotely sensed data alone.     

Cyclic learning rate based HybridSN model for hyperspectral image classification

Classification of remotely sensed hyperspectral images (HSI) is a challenging task due to the presence of a large number of spectral bands and due to the less available data of remotely sensed HSI. The use of 3D-CNN and 2D-CNN layers to extract spectral and spatial features shows good test results. The recently introduced HybridSN model for the classification of remotely sensed hyperspectral images is the best to date compared to the other state-of-the-art models. But the test performance of the HybridSN model decreases significantly with the decrease in training data or number of training epochs. In this paper, we have considered cyclic learning for training of the HybridSN model, which shows a significant increase in the test performance of the HybridSN model with 10%, 20%, and 30% training data and limited number of training epochs. Further, we introduce a new cyclic function (ncf) whose training and test performance is comparable to the existing cyclic learning rate policies. More precisely, the proposed HybridSN(ncf ) model has higher average accuracy compared to HybridSN model by 19.47%, 1.81% and 8.33% for Indian Pines, Salinas Scene and University of Pavia datasets respectively in case of 10% training data and limited number of training epochs.