The objective of this paper is to demonstrate a new capability to detect faint stratospheric aerosols in atmospheric lidar data from NASA’s Cloud-Aerosol Lidar Infrared Pathfinder Satellite Observations (CALIPSO) Mission (12 June 2006 30 June 2023) at high resolution. Faint aerosols from wildfires, distant volcanic eruptions, and Asian and Saharan dust storms play important roles in the Earth-Atmosphere system, as they provide essential air quality and pollution, airline safety, climate radiative forcing, monitoring of fires and volcanic eruptions, environmental safety, and weather forecasting. Tenuous aerosols are recorded in the CALIOP atmospheric lidar data from the CALIPSO mission, but especially extremely faint stratospheric aerosol layers often escape detection and classification partly or entirely in the current CALIOP data analysis scheme. To solve this problem, we introduce a new algorithm for detection and height determination of atmospheric layers, the Density-Dimension Algorithm for CALIOP data analysis (CALIOP-DDA). The DDA is an auto-adaptive algorithm that builds on concepts from artificial intelligence and spatial statistics. Core steps are calculation of a density field and application of a threshold function for signal-noise separation. Stratospheric aerosol detection is aided by the tropopause split concept. The CALIOP-DDA facilitates detection of extremely faint stratospheric aerosols from various sources, including distant wildfires and volcanic eruptions, in night-time and day-time CALIOP data, even in presence of complex types of other cloud and aerosol layers across a large range of optical thicknesses, while retaining the full 334m along-track, 30m height resolution, without creating false positives. CALIOP-DDA results are evaluated by comparison to layer heights derived from airborne validation experiments, conducted using the Cloud Physics Lidar (CPL). In conclusion, the CALIOP-DDA holds promise as the algorithmic basis for a future improved, high-resolution CALIPSO data product.

Grid applications have been prone to encountering problems such as failures or malicious attacks during execution, due to their distributed and large-scale features. The application itself, however, has limited power to address these problems. This paper presents the design, and implementation of an adaptive framework - Dynasa, which strives to handle security problems using adaptive fault-tolerance (i.e., checkpointing and replication) during the execution of applications according to the status of the grid environments.

One of the topics of paramount importance in the development of cluster and grid middleware is the impact of faults since their occurrence in grid infrastructures and in large-scale distributed systems is common. MPI (message passing interface) is a popular abstraction for programming distributed and parallel applications. FAIL (FAult Injection Language) is an abstract language for fault occurrence description capable of expressing complex and realistic fault scenarios. In this paper, we investigate the possibility of using FAIL to inject faults in a fault-tolerant MPI implementation. Our middleware, FAIL-MPI, is used to carry quantitative and qualitative faults and stress testing

A long-term trend in high-performance computing is the increasing number of nodes in parallel computing platforms, which entails a higher failure probability. Fault tolerant programming environments should be used to guarantee the safe execution of critical applications. Research in fault tolerant MPI has led to the development of several fault tolerant MPI environments. Different approaches are being proposed using a variety of fault tolerant message passing protocols based on coordinated checkpointing or message logging. The most popular approach is with coordinated checkpointing. In the literature, two different concepts of coordinated checkpointing have been proposed: blocking and nonblocking. However they have never been compared quantitatively and their respective scalability remains unknown. The contribution of this paper is to provide the first comparison between these two approaches and a study of their scalability. We have implemented the two approaches within the MPICH environments and evaluate their performance using the NAS parallel benchmarks.