This study introduces a systematic methodology whereby different technologies were utilized to download, pre-process, and interactively compare the rainfall datasets from the Integrated Multi-Satellite Retrievals for Global Precipitation Mission (IMERG) satellite and rain gauges. To efficiently handle the large volume of data, we developed automated shell scripts for downloading IMERG data and storing it, along with rain gauge data, in a relational database system. Hypertext pre-processor (pHp) programs were built to visualize the result for better analysis. In this study, the performance of IMERG estimations over the east coast of Peninsular Malaysia for the duration of 10 years (2011–2020) against rain gauge observation data is evaluated. Moreover, this study aimed to improve the daily IMERG estimations with long short-term memory (LSTM) developed with Python. Findings show that the LSTM with Adaptive Moment Estimation (ADAM) optimizer trained against the mean square error (MSE) loss enhances the accuracy of satellite estimations. At the point-to-pixel scale, the correlation between satellite estimations and ground observations was increased by about 15%. The bias was reduced by 81–118%, MAE was reduced by 18–59%, the root-mean-square error (RMSE) was reduced by 1–66%, and the Kling–Gupta efficiency (KGE) was increased by approximately 200%. The approach developed in this study establishes a comprehensive and scalable data processing and analysis pipeline that can be applied to diverse datasets and regions encountering similar domain-specific challenges.

No abstract

Tempe, AZ 85287-5406 bstract An autonomous vehicle equipped with a vision system constantly analyzes 2D images to derive scene descriptions as it navigates around the 3D environment. The derived descriptions heavily influence subsequent actions taken by the vehicle. Deriving scene descriptions requires searching and matching the extracted image features with the model base. The number of possible matches between image features and model features is virtually combinatoric explosion due to instability of features caused by viewpoints. A crucial issue is what type of features to be used for matching. We propose using viewpoint invariance relations (VIRs) resulted from the grouping process by perceptual organization. Examples of VIRs are proximity, collinearity, and parallelism between line segments. Extracting and measuring VIR in a noise-free image is relatively straight forward. This is not the case in practice due to uncertainty inherents in image formation process and imprecision of information obtained from the process. We propose to use fuzzy set theory to deal with this source of uncertainty. Each type of VIR is treated as a fuzzy set characterized by its associated membership function. The membership function is defined by geometric parameters defining the non-fuzzy VIR. The degree to which an image features is a member of a VIR is determined by the associating membership function. The measured degree of membership for each set of image features are aggregated to obtain an overall degree of measure which signifies the degree of evidence to which the unknown is an instance of an object model. 1) IntroductionAn autonomous vehicle equipped with a vision system constantly analyzes 2D images to derive scene descriptions as it navigates around the 3D environment. The derived descriptions heavily influence subsequent actions taken by the vehicle. Deriving scene descriptions requires searching and matching the extracted image features with the model base. The number of possible matches between image features and model features is virtually combinatoric explosion due to instability of features caused by viewpoints. A crucial issue is what type of features to be used for matching. This is the main problem of image segmentation.Image segmentation is a preprocessing stage used in image analysis and understanding in which meaningful image structures are extracted from the image. These structures are then used by higher level processes to derive image descriptions. Image segmentation is an important step in visual understanding because the precision of the outcome of segmentation ultimately will affect the performance of the entire system. Traditionally. there are two approaches used in digital image segmentation: regionbased and edge-based. The region-based approach assumes that feature characteristics within a localized region are relatively constant, whereas the edge-besed approach assumes abrupt changes in one or more features of the borders between regions. In edge-based methods, local edges are detected and then lin...