Search

The use of semi-hypertemporal (SH) satellite data can play an important role in species differentiation based on the physiological and phenological characteristics of different plant species in a forest. Mapping of plant species is essential for addressing problems related to their management and conservation. This study has been conducted to map Acacia catechu from a heterogeneous forest area using SH images in fuzzy-based classifiers. This study has claimed that an individual sample as mean (ISM) training approach outperforms the conventional mean-based approach for selecting the training samples for fuzzy-based possibilistic $c$ means (PCM), noise clustering (NC), and modified PCM (MPCM) algorithms. Furthermore, the SH dataset is found to be better for a particular species extraction in contrast to the single date image, using both the conventional and ISM approaches. Moreover, an increasing number of images in the SH dataset produces significantly better classification outputs. This study can be used to map the endangered species with improved classification accuracy and for better management practices. [ABSTRACT FROM AUTHOR]

In this research work, non-linearity in data has been handled by incorporating kernel with the Modified Possibilistic c-Means (MPCM) algorithm. Nine different types of kernel function have been proposed to classify nine different classes and have non-linearity among them. Gaussian has been identified as the best performing kernel at an optimized fuzzified value m = 1.5 with an overall accuracy 92.45%. The composite kernels have been generated with an aim of improvement of accuracy in comparison to single kernel. Further, role of spatial constraints has been analyzed by adding neighboring pixel information to handle the noise. It was observed that overall accuracy depends on the spatial parameter that has been included. Thus, local information having local similarity measure parameters (Sir)in the image produces highest accuracy compared to others. Moreover, the identified best kernel (Gaussian Kernel) has been then used for extraction of the burnt paddy fields in a different test site. [ABSTRACT FROM AUTHOR]

In this study, temporal MODIS-Terra MOD13Q1 data have been used for identification of wheat crop uniquely, using the noise clustering (NC) soft classification approach. This research also optimises the selection of date combination and vegetation index for classification of wheat crop. First, a separability analysis is used to optimise the date combination for each case of number of dates and vegetation index. Then, these scenes have undergone for NC soft classification. The resolution parameter (δ) was optimised for the NC classifier and found to be a value of 1.6 × 104for wheat crop identification. Classified outputs were analysed by receiver operating characteristics (ROC) analysis for sub-pixel detection. Highest area under the ROC curve was found for soil-adjusted vegetation index corresponding to the three different phenological stages data sets. From this study, the data sets corresponding to the Sowing, Flowering and Maturity phenological stages of wheat crop were found more suitable to identify it uniquely. [ABSTRACT FROM PUBLISHER]

The present research aims to extract moist deciduous forest (MDF) from Moderate Resolution Imaging Spectroradiometer (MODIS) temporal data by using the fuzzyc-means (FCM)-based noise clustering (NC) soft classification approach. Seven-date temporal MODIS data were used to identify MDF, and temporal Advanced Wide Field Sensor (AWiFS) data were used as reference data for testing. Different types of spectral indices were used to generate the temporal data set combinations for both MODIS and AWiFS. The NC resolution parameter deltawas optimized to achieve the best output. It was found that for both AWiFS and MODIS data, optimum NC outputs were obtained whenreached close to 105. For assessment of the accuracy, NC classified outputs were optimized using the entropy approach. The optimized data set of AWiFS was then used for assessing the accuracy of the optimized data set of MODIS using fuzzy error matrix (FERM), composite operators (MIN-MIN, MIN-PROD, and MIN-LEAST), and a sub-pixel confusion-uncertainty matrix (SCM). It was found that the temporal data set combination corresponding to ‘Three’ date yields the highest overall accuracy for all accuracy assessment techniques. In all cases, the ‘Three’ date combination corresponds to the three scenes pertaining to different phenological activity of the MDF. This ‘Three’ date combination, along with the soil-adjusted vegetation index (SAVI), yielded the highest overall accuracy values, namely 94.88% and 94.84% for MIN-LEAST and MIN-PROD, respectively. [ABSTRACT FROM AUTHOR]

Abstract: The two soft fuzzy based classifiers, Possibilistic c-Means (PCM) approach and Noise Clustering (NC) were compared for the Moist Deciduous Forest (MDF) identification from MODIS temporal data. Seven date temporal MODIS data were used to identify MDF and temporal Advanced Wide Field Sensor (AWiFS) data was used as reference data for testing. Simple Ratio (SR), Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI) and Enhanced Vegetation Index 2 (EVI2) were used to generate the temporal spectral index datasets for both the MODIS and AWiFS. The parameter weighting exponent m for PCM and resolution parameter δ for NC were optimized. Results show that the optimized value of m for MDF is 2.1, while δ value is 3.6×104 for temporal MODIS data. For assessment of the accuracy AWiFS datasets were also optimized using entropy approach. The optimized dataset of AWiFS was then used for accuracy assessment of the soft classified outputs from MODIS using Fuzzy ERror Matrix (FERM). It was found from this study that, for PCM classifier the highest fuzzy overall accuracy of 97.44% was obtained using the SAVI for the temporal dataset ‘Five’ consisting to one scene of ‘Full greenness’, three scenes in ‘Intermediate frequency stage of Onset of Greenness (OG) and End of Senescence (ES) activity’ and the last image pertaining corresponds to the ‘Maximum frequency stage of OG activity’ as per phenology of MDF. Similarly, for NC classifier the highest fuzzy overall accuracy of 95.19% was obtained for the EVI2 with temporal dataset ‘Five’ consisting with two scene of ‘Full greenness’, two scenes in ‘Intermediate frequency stage of OG and ES activity’ and the last one corresponds to the ‘Maximum frequency stage of OG activity’as per phenology of MDF. [Copyright &y& Elsevier]

Deep learning-based frameworks have not been much explored to incorporate the temporal dimension of the remote sensing data. In this research work, deep learning-based models have been developed which exploit the spectral-temporal domain of bi-sensor remote sensing data obtained from Sentinel-2 and Landsat-8 satellites. Application of proposed deep learning frameworks has been tested for mapping transplanted paddy fields using Class Based Sensor Independent - Normalised Difference Vegetation Index (CBSI-NDVI) spectral reduction approach. Two deep learning-based models viz., one-dimensional Convolutional Neural Network (1-D CNN) and hybrid 1-D Convolutional Neural Network – Long Short Term Memory (CNN-LSTM) consisting of 1-D CNN and LSTM layers respectively were developed. For both of the models the optimized model hyper-parameters were also deduced. Though the performance of both the models were above satisfactory level still the 1-D CNN model performed slightly better than the hybrid 1-D CNN-LSTM based model with average overall accuracies of 93.75% and 91.25% respectively. The average F-measure values were computed as 0.93 and 0.90 respectively for the 1-D CNN based and hybrid CNN-LSTM based models. This study indicates that 1-D CNN based deep learning models provide an effective solution to handle mono/bi-sensor temporal remote sensing data of medium spatial resolution with small size training datasets. • Deep learning-based models have been tested for mapping transplanted paddy fields. • 1-D CNN model has been proven an effective solution to handle mono/bi-sensor temporal remote sensing data. [ABSTRACT FROM AUTHOR]