At equatorial latitudes, ionospheric scintillation is the major limitation in achieving high-accuracy GNSS positioning. This is because scintillation affects the tracking ability of GNSS receivers causing losses of lock and degradation on code pseudorange and carrier phase measurements, thus degrading accuracy. During strong ionospheric scintillation, such effects are more severe and GNSS users cannot rely on the integrity, reliability, and availability required for safety-critical applications. In this paper, we propose a novel approach able to greatly reduce these effects of scintillation on precise point positioning (PPP). Our new approach consists of three steps: 1) a new functional model that corrects the effects of range errors in the observables; 2) a new stochastic model that uses these corrections to generate more accurate positioning; and 3) a new strategy to attenuate the effects of losses of lock and consequent ambiguities re-initializations that are caused by the need to re-initialize the tracking. We demonstrate the effectiveness of our method in an experiment using a 30-day static dataset affected by different levels of scintillation in the Brazilian southeastern region. Even with limitations imposed by data gaps, our results demonstrate improvements of up to 80% in the positioning accuracy. We show that, in the best cases, our method can completely negate the effects of ionospheric scintillation and can recover the original PPP accuracy that would have existed without any scintillation. The significance of this paper lies in the improvement it offers in the integrity, reliability, and availability of GNSS services and applications.

Clouds are one of the major limitations to crop monitoring using optical satellite images. Despite all efforts to provide decision-makers with high-quality agricultural statistics, there is still a lack of techniques to optimally process satellite image time series in the presence of clouds. In this regard, in this article it was proposed to add a Multi-Layer Perceptron loss function to the pix2pix conditional Generative Adversarial Network (cGAN) objective function. The aim was to enforce the generative model to learn how to deliver synthetic pixels whose values were proxies for the spectral response improving further crop type mapping. Furthermore, it was evaluated the generalization capacity of the generative models in producing pixels with plausible values for images not used in the training. To assess the performance of the proposed approach it was compared real images with synthetic images generated with the proposed approach as well as with the original pix2pix cGAN. The comparative analysis was performed through visual analysis, pixel values analysis, semantic segmentation and similarity metrics. In general, the proposed approach provided slightly better synthetic pixels than the original pix2pix cGAN, removing more noise than the original pix2pix algorithm as well as providing better crop type semantic segmentation; the semantic segmentation of the synthetic image generated with the proposed approach achieved an F1-score of 44.2%, while the real image achieved 44.7%. Regarding the generalization, the models trained utilizing different regions of the same image provided better pixels than models trained using other images in the time series. Besides this, the experiments also showed that the models trained using a pair of images selected every three months along the time series also provided acceptable results on images that do not have cloud-free areas.

Road extraction is still a challenging topic for researchers. Currently, deep convolution neural networks are state-of-the-art in road network segmentation and are known for their remarkable ability to explore multilevel contexts. Despite this, the architectures still suffer from occlusion and obstructions that cause discontinuities and omissions in extracted road networks. Generally, these effects are minimized with strategies to obtain the context of the scene and not explore the complementarity of knowledge from a diversity of sources. We propose an early fusion network with RGB and surface model images that provide complementary geometric data to improve road surface extraction. Our results demonstrate that Unet_early reaches 71.01% intersection over union (IoU) and 81.95% F1, and the fusion strategy increases the IoU and F1 scores at 2.3% and 1.5%, respectively. Besides, it overpassed the best model without fusion (DeepLabv3+). The Brazilian dataset and architecture implementation are available at https://github.com/tunofilho/ieee_road_multimodal .