CyberSoLIM: A cyber platform for digital soil mapping

Vestn. Ross. univ. družby nar., Ser. Agron. životnovod.

Qin

Liang

et al. 2018

Self Cite

The key challenges faced by many of the existing digital soil mapping (DSM) techniques are the rigid requirements on the size of soil samples to extract the relationships needed and on the stationarity of the extracted relationships. These requirements limit the application of these DSM techniques. This paper provides an overview of the SoLIM approach and an introduction to the operation of SoLIM through the software platforms available. SoLIM is based on the Third Law of Geography, which calls for the comparison of similarity in geographic (environmental) configuration of a prototype and an unsampled location and then use this similarity to predict the value of a soil property at a given location. DSM under SoLIM approach removes requirements on the sample size and the stationarity assumption. In addition, the uncertainty computed based on the similarities can be used to improve the efficiency of error reduction efforts. The SoLIM approach has been implemented in two platforms: SoLIM Solutions and CyberSoLIM. The theoretical foundation and the availability of software platforms under SoLIM make DSM possible and convenient over large and complex geographic regions.

Section: Cybersolimmentioning

confidence: 99%

Digital Soil Mapping for Smart Agriculture: The Solim Method and Software Platforms

Vestn. Ross. univ. družby nar., Ser. Agron. životnovod.

Qin

Liang

et al. 2018

Self Cite

“…For example, Jiang et al. (2016) developed a cyber platform for DSM using an HPC server as the computing back‐end where the DSM algorithms were implemented using OpenMP (Open Multi‐Processing) and run on multi‐core central processing units (CPUs). In mapping soil series at 30‐m resolution over the contiguous United States, Chaney et al.…”

Section: Introductionmentioning

confidence: 99%

“…Training deep learning models is computationally intensive and thus parallel computing resources on multi‐CPUs or GPUs are exploited to speed up model training, for example, using Google's TensorFlow (Abadi et al., 2016). Lastly, as aforementioned, some specialized DSM algorithms have been parallelized over multi‐core CPUs (e.g., Jiang et al., 2016) or over supercomputer computing nodes (Chaney et al., 2016). Overall, there is a lack of implementations of DSM algorithms exploiting the massively parallel computing power of GPUs to speed up DSM applications.…”

Section: Introductionmentioning

confidence: 99%

PyCLiPSM: Harnessing heterogeneous computing resources on CPUs and GPUs for accelerated digital soil mapping

Zhang

Liu

et al. 2021

Transactions in GIS

Self Cite

Digital soil mapping (DSM) at high spatial resolutions over large areas often demands considerable computing power. This study aims to harness the heterogeneous computing resources on multi‐core central processing units (CPUs) and graphics processing units (GPUs) to accelerate DSM by implementing PyCLiPSM, a parallel version of the iPSM (individual predictive soil mapping) algorithm which represents the type of geospatial algorithms that is data‐ and compute‐intensive and highly parallelizable. PyCLiPSM was implemented in Python based on the PyOpenCL parallel programming library, which runs on any operating system and exploits the computing power of both CPUs and GPUs. Experiments show that PyCLiPSM can effectively leverage multi‐core CPUs and GPUs to speed up DSM tasks. PyCLiPSM is open‐source and freely available. Using PyCLiPSM as an example, we advocate implementing parallel geospatial algorithms using the PyOpenCL framework to harness the heterogeneous computing resources available to researchers and practitioners for accelerated geospatial analysis.

“…This type of intelligent workflow building methods of input data preparation can (semi-)automatically discover and compose the needed data processing algorithms (or web services) based on semantic matching and reasoning. For example, the heuristic modeling proposed by Jiang, et al [92] adopts RDF, heuristic modeling, and backward chaining approaches to semi-automatically build abstract workflows. The method starts by selecting an algorithm that can generate outputs matching user-specified target data (i.e., input data for the users' geographic model).…”

mentioning

confidence: 99%

“…This procedure is repeated until all the input data of the workflow are available. Besides this heuristic modeling proposed by Jiang et al [92], other researchers have used ontologies, logical reasoning, and forward-chaining or backward-chaining approaches to automatically discover and compose the required services according to users' requests [32,93,94]. The match between users' requests and inputs, outputs, preconditions, and effects/postconditions (IOPE) semantics of web services is based on semantic matching and logical reasoning, such as description logic (DL) reasoning, first-order logic (FOL) reasoning, and rule-based reasoning.…”

mentioning

confidence: 99%

From Manual to Intelligent: A Review of Input Data Preparation Methods for Geographic Modeling

Hou

Qin

et al. 2019

IJGI

Self Cite

One of the key concerns in geographic modeling is the preparation of input data that are sufficient and appropriate for models. This requires considerable time, effort, and expertise since geographic models and their application contexts are complex and diverse. Moreover, both data and data pre-processing tools are multi-source, heterogeneous, and sometimes unavailable for a specific application context. The traditional method of manually preparing input data cannot effectively support geographic modeling, especially for complex integrated models and non-expert users. Therefore, effective methods are urgently needed that are not only able to prepare appropriate input data for models but are also easy to use. In this review paper, we first analyze the factors that influence data preparation and discuss the three corresponding key tasks that should be accomplished when developing input data preparation methods for geographic models. Then, existing input data preparation methods for geographic models are discussed through classifying into three categories: manual, (semi-)automatic, and intelligent (i.e., not only (semi-)automatic but also adaptive to application context) methods. Supported by the adoption of knowledge representation and reasoning techniques, the state-of-the-art methods in this field point to intelligent input data preparation for geographic models, which includes knowledge-supported discovery and chaining of data pre-processing functionalities, knowledge-driven (semi-)automatic workflow building (or service composition in the context of geographic web services) of data preprocessing, and artificial intelligent planning-based service composition as well as their parameter-settings. Lastly, we discuss the challenges and future research directions from the following aspects: Sharing and reusing of model data and workflows, integration of data discovery and processing functionalities, task-oriented input data preparation methods, and construction of knowledge bases for geographic modeling, all assisting with the development of an easy-to-use geographic modeling environment with intelligent input data preparation.