Group intelligence algorithms have been widely used in support vector machine (SVM) parameter optimization due to their obvious characteristics of strong parallel processing ability, fast optimization, and global optimization. However, few studies have made optimization performance comparisons of different group intelligence algorithms on SVMs, especially in terms of their application to hyperspectral remote sensing classification. In this paper, we compare the optimization performance of three different group intelligence algorithms that were run on a SVM in terms of five aspects by using three hyperspectral images (one each of the Indian Pines, University of Pavia, and Salinas): the stability to parameter settings, convergence rate, feature selection ability, sample size, and classification accuracy. Particle swarm optimization (PSO), genetic algorithms (GAs), and artificial bee colony (ABC) algorithms are the three group intelligence algorithms. Our results showed the influence of these three optimization algorithms on the C-parameter optimization of the SVM was less than their influence on the σ-parameter. The convergence rate, the number of selected features, and the accuracy of the three group intelligence algorithms were statistically significant different at the p = 0.01 level. The GA algorithm could compress more than 70% of the original data and it was the least affected by sample size. GA-SVM had the highest average overall accuracy (91.77%), followed by ABC-SVM (88.73%), and PSO-SVM (86.65%). Especially, in complex scenes (e.g., the Indian Pines image), GA-SVM showed the highest classification accuracy (87.34%, which was 8.23% higher than ABC-SVM and 16.42% higher than PSO-SVM) and the best stability (the standard deviation of its classification accuracy was 0.82%, which was 5.54% lower than ABC-SVM, and 21.63% lower than PSO-SVM). Therefore, when compared with the ABC and PSO algorithms, the GA had more advantages in terms of feature band selection, small sample size classification, and classification accuracy.

Accurate evaluation of start of season (SOS) changes is essential to assess the ecosystem’s response to climate change. Smoothing method is an understudied factor that can lead to great uncertainties in SOS extraction, and the applicable situation for different smoothing methods and the impact of smoothing parameters on SOS extraction accuracy are of critical importance to be clarified. In this paper, we use MOD13Q1 normalized difference vegetation index (NDVI) data and SOS observations from eight agrometeorological stations on the Qinghai–Tibetan Plateau (QTP) during 2001–2011 to compare the SOS extraction accuracies of six popular smoothing methods (Changing Weight (CW), Savitzky-Golay (SG), Asymmetric Gaussian (AG), Double-logistic (DL), Whittaker Smoother (WS) and Harmonic Analysis of NDVI Time-Series (HANTS)) for two types of different SOS extraction methods (dynamic threshold (DT) with 9 different thresholds and double logistic (Zhang)). Furthermore, a parameter sensitivity analysis for each smoothing method is performed to quantify the impacts of smoothing parameters on SOS extraction. Finally, the suggested smoothing methods and reference ranges for the parameters of different smoothing methods were given for grassland phenology extraction on the QTP. The main conclusions are as follows: (1) the smoothing methods and SOS extraction methods jointly determine the SOS extraction accuracy, and a bad denoising performance of smoothing method does not necessarily lead to a low SOS extraction accuracy; (2) the default parameters for most smoothing methods can result in acceptable SOS extraction accuracies, but for some smoothing methods (e.g., WS) a parameter optimization is necessary, and the optimal parameters of the smoothing method can increase the R² and reduce the RMSE of SOS extraction by up to 25% and 331%; (3) The main influencing factor of the SOS extraction using the DT method is the stability of the minimum value in the NDVI curve, and for the Zhang method the curve shape before the peak of the NDVI curve impacts the most; (4) HANTS is the most stable method no matter with (fitness = 35.05) or without parameter optimization (fitness = 33.52), which is recommended for QTP grassland SOS extraction. The findings of this study imply that remote sensing-based vegetation phenology extraction can be highly uncertain, and a careful selection and parameterization of the time-series smoothing method should be taken to achieve an accurate result.

Cloud contamination has largely limited the application of the Moderate Resolution Imaging Spectroradiometer(MODIS) normalized difference snow index (NDSI). Here, a novel gap-filling method based on spatial-temporal similar pixel interpolation was proposed to remove cloud occlusions in MODIS NDSI products. First, the widely used Terra and Aqua combination and three-day temporal filter methods were applied. The remaining missing NDSI information was estimated by using similar eligible pixels in the remaining cloud-free portion of a target image through a spatial-temporal similar pixel selecting algorithm (SPSA). The MODIS daily NDSI product data from 2003 to 2018 in the Qinghai–Tibetan Plateau (China) was used as a case study. The results demonstrate that the three-step methodology can generate almost completely cloud-free, daily MODIS NDSI images, reducing the cloud-gap fraction from >45% to less than 1.5% on average. The validation results of the SPSA method exhibited a high accuracy, with a high R² exceeding 0.78, a low mean absolute error of 2.77%, a root mean square error of 3.78%, and a 96.92% overall accuracy. The proposed method can fill cloud gaps without a significant loss of accuracy, especially during snow cover transition periods (autumn and spring), which may provide more accurate cloud-free NDSI data for climate change and energy balance studies.