scholarly journals Evaluating the potential of Genetic Programming as an exploratory data analysis in soil science

2018 ◽  
Author(s):  
Lorenzo Menichetti ◽  
Alberto Tonda
Keyword(s):  
Data Analysis ◽  
Soil Respiration ◽  
Genetic Programming ◽  
Soil Properties ◽  
Search Algorithm ◽  
Optimization Technique ◽  
Symbolic Regression ◽  
Environmental Modeling ◽  
Soil Science ◽  
Pedotransfer Functions

Genetic Programming is a powerful optimization technique, able to deliver high-quality results in several real-world problems. One of its most successful applications is symbolic regression, where the objective is to find a suitable expression to model the underlying relationship between data points, with no aprioristic assumptions. In this paper, we propose the application of a Genetic Programming technique to a dataset on soil respiration and soil properties, in order to investigate possible influences of soil properties on soil respiration through symbolic regression. The best candidate models obtained by the technique are then studied to determine possible differences in the relationships related to environmental factors. Recurring patterns in the best solutions proposed by the search algorithm are identified, and the suitability of symbolic regression in soil science is evaluated and discussed. Genetic Programming proves to be an extremely promising data mining technique for soil scientists, as it is able to uncover relationships that could otherwise remain hidden, while remaining completely neutral and bias-free. We suggest its application for routine data analysis, as the technique presents particular interest for environmental modeling and development of pedotransfer functions.

scholarly journals Diagnostic role of soil physical properties of forest biogeocoenoses of the Ukrainian steppe zone

2018 ◽  
Vol 29 (2) ◽  
Author(s):  
V. A. Gorban
Keyword(s):  
Physical Properties ◽  
Soil Properties ◽  
Granulometric Composition ◽  
Steppe Zone ◽  
Diagnostic Value ◽  
Soil Physical Properties ◽  
Soil Science ◽  
Pedotransfer Functions ◽  
Diagnostic Feature ◽  
Aggregate Composition

For the current stage of the development of soil science it is relevant to search for objectively existing interactions between the various soil properties. Solving this issue most appropriately should be based on the establishment of pedotransfer functions. Pedotransfer functions appeared at the time of the birth of quantitative soil science, when one of the properties of the soil tried to predict others when it became clear that everything in the soil is interrelated when it was established that there is a well-defined number of fundamental, basic properties of the soil, which is basically defines its other properties. Accordingly, the purpose of our work is to establish the diagnostic value of the individual soil physical properties of forest biogeocoenoses of the steppe by means of determining the existing interconnections between them and other properties and characteristics of these soils. The solution of this issue is one of the tasks of developing research on the soil physical properties of forest biogeocoenoses of the Ukrainian steppe zone. The diagnostic value of granulometric and structural-aggregate composition, density and permeability for determining the general state of soils due to the existence of certain interactions between the indicated parameters and other soil properties is considered. The granulometric composition is a fundamental soil characteristic that determines not only the physical state, but also all the main soil properties and regimes of forest biogeocoenoses of the Ukrainian steppe zone. The structural and aggregate composition is an important complex diagnostic feature of chernozem, which helps to reveal the peculiarities of their genesis under the influence of forest vegetation, in particular as a result of changes in the content and composition of organic matter, exchange cations, the influence of root vegetation systems, etc. The soil density, due to existing interactions with other soil properties, is an important diagnostic feature that reflects the features of their genesis and regimes, which determines the specificity of the ecological functions of the soils of forest biogeocoenoses of the Ukrainian steppe zone. Water permeability can be considered as a complex characteristic of soils, which to a certain extent reflects their granulometric composition, porosity, structural and aggregate composition, determines the features of the water-air regime. The differences of physical properties of zonal chernozems and chernozems, the genesis of which are connected with artificial and natural forest biogeocoenoses within the steppe zone of Ukraine, are analyzed. The relevance of the further search for relationships between physical indicators that are easily and promptly analyzed, and other soil properties for expanding diagnostic possibilities with respect to their genesis is pointed out.

scholarly journals Control Synthesis as Machine Learning Control by Symbolic Regression Methods

2021 ◽  
Vol 11 (12) ◽  
pp. 5468
Author(s):  
Elizaveta Shmalko ◽  
Askhat Diveev
Keyword(s):  
Machine Learning ◽  
Genetic Programming ◽  
Mathematical Formulation ◽  
Small Variation ◽  
Learning Control ◽  
Symbolic Regression ◽  
Control Technique ◽  
Control Synthesis ◽  
Basic Solution ◽  
Regression Methods

The problem of control synthesis is considered as machine learning control. The paper proposes a mathematical formulation of machine learning control, discusses approaches of supervised and unsupervised learning by symbolic regression methods. The principle of small variation of the basic solution is presented to set up the neighbourhood of the search and to increase search efficiency of symbolic regression methods. Different symbolic regression methods such as genetic programming, network operator, Cartesian and binary genetic programming are presented in details. It is shown on the computational example the possibilities of symbolic regression methods as unsupervised machine learning control technique to the solution of MLC problem of control synthesis for obtaining the stabilization system for a mobile robot.

Optimizing the Learning Process of Feedforward Neural Networks Using Lightning Search Algorithm

2016 ◽  
Vol 25 (06) ◽  
pp. 1650033 ◽  
Author(s):  
Hossam Faris ◽  
Ibrahim Aljarah ◽  
Nailah Al-Madi ◽  
Seyedali Mirjalili
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Optimization Problems ◽  
Search Algorithm ◽  
Optimization Technique ◽  
Back Propagation ◽  
Feedforward Neural Networks ◽  
Training Algorithms ◽  
Local Optima ◽  
Local Solutions

Evolutionary Neural Networks are proven to be beneficial in solving challenging datasets mainly due to the high local optima avoidance. Stochastic operators in such techniques reduce the probability of stagnation in local solutions and assist them to supersede conventional training algorithms such as Back Propagation (BP) and Levenberg-Marquardt (LM). According to the No-Free-Lunch (NFL), however, there is no optimization technique for solving all optimization problems. This means that a Neural Network trained by a new algorithm has the potential to solve a new set of problems or outperform the current techniques in solving existing problems. This motivates our attempts to investigate the efficiency of the recently proposed Evolutionary Algorithm called Lightning Search Algorithm (LSA) in training Neural Network for the first time in the literature. The LSA-based trainer is benchmarked on 16 popular medical diagnosis problems and compared to BP, LM, and 6 other evolutionary trainers. The quantitative and qualitative results show that the LSA algorithm is able to show not only better local solutions avoidance but also faster convergence speed compared to the other algorithms employed. In addition, the statistical test conducted proves that the LSA-based trainer is significantly superior in comparison with the current algorithms on the majority of datasets.

Statistical genetic programming for symbolic regression

2017 ◽  
Vol 60 ◽  
pp. 447-469 ◽  
Author(s):  
Maryam Amir Haeri ◽  
Mohammad Mehdi Ebadzadeh ◽  
Gianluigi Folino
Keyword(s):  
Genetic Programming ◽  
Symbolic Regression

scholarly journals A NEW LINEAR GENETIC PROGRAMMING APPROACH BASED ON STRAIGHT LINE PROGRAMS: SOME THEORETICAL AND EXPERIMENTAL ASPECTS

2009 ◽  
Vol 18 (05) ◽  
pp. 757-781 ◽  
Author(s):  
CÉSAR L. ALONSO ◽  
JOSÉ LUIS MONTAÑA ◽  
JORGE PUENTE ◽  
CRUZ ENRIQUE BORGES
Keyword(s):  
Data Structure ◽  
Genetic Programming ◽  
Computer Programs ◽  
Symbolic Regression ◽  
Programming Approach ◽  
Linear Genetic Programming ◽  
Straight Line ◽  
Structured Representations ◽  
Regression Problems ◽  
Straight Line Programs

Tree encodings of programs are well known for their representative power and are used very often in Genetic Programming. In this paper we experiment with a new data structure, named straight line program (slp), to represent computer programs. The main features of this structure are described, new recombination operators for GP related to slp's are introduced and a study of the Vapnik-Chervonenkis dimension of families of slp's is done. Experiments have been performed on symbolic regression problems. Results are encouraging and suggest that the GP approach based on slp's consistently outperforms conventional GP based on tree structured representations.

Potential Soil Respiration and Relationship to Soil Properties in Ridge Tillage

1995 ◽  
Vol 59 (5) ◽  
pp. 1430-1435 ◽  
Author(s):  
M. A. Liebig ◽  
A. J. Jones ◽  
J. W. Doran ◽  
L. N. Mielke
Keyword(s):  
Soil Respiration ◽  
Soil Properties ◽  
Ridge Tillage

Regional characterisation of soil properties by combining soil science and hyperspectral and thermal remote sensing: A technical overview of lab and field remote sensing methods

2021 ◽  
Author(s):  
Richard Mommertz ◽  
Lars Konen ◽  
Martin Schodlok
Keyword(s):  
Remote Sensing ◽  
Soil Properties ◽  
Regional Scale ◽  
Arable Land ◽  
Soil Mapping ◽  
Soil Science ◽  
Near Surface ◽  
Soil Parameter ◽  
The Impact ◽  
Parameter Retrieval

<p>Soil is one of the world’s most important natural resources for human livelihood as it provides food and clean water. Therefore, its preservation is of huge importance. For this purpose, a proficient regional database on soil properties is needed. The project “ReCharBo” (Regional Characterisation of Soil Properties) has the objective to combine remote sensing, geophysical and pedological methods to determine soil characteristics on a regional scale. Its aim is to characterise soils non-invasive, time and cost efficient and with a minimal number of soil samples to calibrate the measurements. Konen et al. (2021) give detailed information on the research concept and first field results in a presentation in the session “SSS10.3 Digital Soil Mapping and Assessment”. Hyperspectral remote sensing is a powerful and well known technique to characterise near surface soil properties. Depending on the sensor technology and the data quality, a wide variety of soil properties can be derived with remotely sensed data (Chabrillat et al. 2019, Stenberg et al. 2010). The project aims to investigate the effects of up and downscaling, namely which detail of information is preserved on a regional scale and how a change in scales affects the analysis algorithms and the possibility to retrieve valid soil parameter information. Thus, e.g. laboratory and field spectroscopy are applied to gain information of samples and fieldspots, respectively. Various UAV-based sensors, e.g. thermal & hyperspectral sensors, are applied to study soil properties of arable land in different study areas at field scale. Finally, airborne (helicopter) hyperspectral data will cover the regional scale. Additionally forthcoming spaceborne hyperspectral satellite data (e.g. Prisma, EnMAP, Sentinel-CHIME) are a promising outlook to gain detailed regional soil information. In this context it will be discussed how the multisensor data acquisition is best managed to optimise soil parameter retrieval. Sensor specific properties regarding time and date of acquisition as well as weather/atmospheric conditions are outlined. The presentation addresses and discusses the impact of a multisensor and multiscale remote sensing data collection regarding the results on soil parameter retrieval.</p><p> </p><p>References</p><p>Chabrillat, S., Ben-Dor, E. Cierniewski, J., Gomez, C., Schmid, T. & van Wesemael, B. (2019): Imaging Spectroscopy for Soil Mapping and Monitoring. Surveys in Geophysics 40:361–399. https://doi.org/10.1007/s10712-019-09524-0</p><p>Stenberg, B., Viscarra Rossel, R. A., Mounem Mouazen, A. & Wetterlind, J. (2010): Visible and Near Infrared Spectroscopy in Soil Science. In: Donald L. Sparks (editor): Advances in Agronomy. Vol. 107. Academic Press:163-215. http://dx.doi.org/10.1016/S0065-2113(10)07005-7</p>

Sign in / Sign up

Export Citation Format

Share Document