ESTIMATING CO<sub>2</sub> EMISSIONS FROM TILLED SOILS THROUGH ARTIFICIAL NEURAL NETWORKS AND MULTIPLE LINEAR REGRESSION<sup>1</sup>

VITÓRIA, EDNEY LEANDRO DA; SIMON, CARLA DA PENHA; LACERDA, ELCIO DAS GRAÇA; FREITAS, ISMAEL LOURENÇO DE JESUS; GONTIJO, IVONEY

doi:10.1590/1983-21252022v35n424rc

Acessibilidade / Reportar erro

Brasil

Español English

sumário « anterior atual seguinte »

Sumário

Technical Note • Rev. Caatinga 35 (4) • Oct-Dec 2022 • https://doi.org/10.1590/1983-21252022v35n424rc copy

ESTIMATING CO₂ EMISSIONS FROM TILLED SOILS THROUGH ARTIFICIAL NEURAL NETWORKS AND MULTIPLE LINEAR REGRESSION¹

ESTIMATIVAS DE EMISSÃO DE CO₂ EM SOLOS CULTIVADOS POR MEIO DE REDES NEURAIS ARTIFICIAS E MODELO LINEAR DE REGRESSÃO

Authorship SCIMAGO INSTITUTIONS RANKINGS

ABSTRACT

Quantifying soil gas emissions is costly, since it requires specific methodologies and equipment. The objective of this study was to evaluate modeling by nonlinear regression and artificial neural networks (ANN) to estimate CO₂ emissions caused by soil managements. CO₂ emissions were evaluated in two different soil management systems: no-tillage and minimum tillage. Readings of CO₂ flow were carried out by an automated closed system chamber; soil temperature, water content, density, and total organic carbon were also determined. The regression model and the ANN models were adjusted based on the correlation of the variables measured in the areas where the soil was managed with no-tillage and minimum tillage with data of CO₂ emission. Artificial neural networks are more accurate to determine correlations between CO₂ emissions and soil temperature, water content, density, and organic carbon content than linear regression.

Keywords
Greenhouse gases; Soil management; Modeling; Artificial intelligence.

Management system	Variable	Minimum	Mean	Maximum	CV (%)	W
	C-CO₂ (μmol m^-2)	0.88	2.30a	5.98	37.0	0.043^* * non-normal distribution.
	T (°C)	27.6	32.4a	38.0	10.3	0.040^* * non-normal distribution.
NTS	SH (m³ m^-3)	0.040	0.107a	0.163	12.1	0.032^* * non-normal distribution.
	SD (g cm^-3)	1.22	1.37a	1.48	7.71	0.015^* * non-normal distribution.
	TOC (g kg^-1)	8.23	15.30a	24.2	10.6	0.022^* * non-normal distribution.
	C-CO₂ (μmol m^-2)	0.92	2.25a	6.01	40.2	0.049^* * non-normal distribution.
	T (°C)	26.9	35.7a	38.8	11.2	0.051^* * non-normal distribution.
MTS	SH (m³ m^-3)	0.040	0.093a	0.156	15.0	0.025^* * non-normal distribution.
	SD (g cm^-3)	1.26	1.43a	1.47	7.69	0.019^* * non-normal distribution.
	TOC (g kg^-1)	8.25	12.3b	26.1	12.7	0.005^* * non-normal distribution.

		No-tillage	system
C-CO₂	C-CO₂ 1	T	SH	SD	TOC
T	0.58^* * Significant by the t test (p<0.05).	1
SH	-0.25^* * Significant by the t test (p<0.05).	0.58^* * Significant by the t test (p<0.05).	1
SD	0.15^ns	-0.25^* * Significant by the t test (p<0.05).	-0.40^* * Significant by the t test (p<0.05).	1
TOC	0.79^* * Significant by the t test (p<0.05).	0.15^ns	0.11^ns	-0.30^ns	1
Minimum-tillage system
C-CO₂	C-CO₂ 1	T	SH	SD	TOC
T	0.63^* * Significant by the t test (p<0.05).	1
SH	-0.31^* * Significant by the t test (p<0.05).	0.47^* * Significant by the t test (p<0.05).	1
SD	0.19^ns	-0.25^ns	-0.36^* * Significant by the t test (p<0.05).	1
TOC	0.66^* * Significant by the t test (p<0.05).	0.18^ns	0.18^ns	-0.22^ns	1

Management system	^β0	^β1	^β2	^β3	^β4	Adjustment	Validation	t test
Management system	^β0	^β1	^β2	^β3	^β4	RMSE r_cĉ (%)	r _c_ĉ RMSE _%	t test
NTS	5.325^*	0.021^*	-2.832^ns	0.066^ns	0.165^*	0.706 18.193	0.691 18.424	0.232^ns
MTS	6.023^*	0.033^*	-3.118”	0.102^ns	0.213^*

ANN	Training			Validation	t test
	r_cĉ	RMSE%	r_cĉ	RMSE%
1	0.863	9.12	0.849	9.47	0.238^ns
2	0.849	9.17	0.848	9.51	0.253^ns
3	0.851	9.23	0.849	9.49	0.227^ns
4	0.862	9.34	0.847	9.59	0.292^ns

	Adjustment				Validation
	rcĉ	RMSE%	d	CS	rcĉ	RMSE%	d	CS
MLR	0.706	18.19	0.711	0.501	0.691	18.42	0.694	0.479
ANN 1	0.863	9.12	0.862	0.733	0.849	9.47	0.851	0.722

Universidade Federal Rural do Semi-Árido Avenida Francisco Mota, número 572, Bairro Presidente Costa e Silva, Cep: 5962-5900, Telefone: 55 (84) 3317-8297 - Mossoró - RN - Brazil
E-mail: caatinga@ufersa.edu.br

Acompanhe os números deste periódico no seu leitor de RSS

[1] *Corresponding author

Brasil

Brasil

ESTIMATING CO2 EMISSIONS FROM TILLED SOILS THROUGH ARTIFICIAL NEURAL NETWORKS AND MULTIPLE LINEAR REGRESSION1

ESTIMATIVAS DE EMISSÃO DE CO2 EM SOLOS CULTIVADOS POR MEIO DE REDES NEURAIS ARTIFICIAS E MODELO LINEAR DE REGRESSÃO

ABSTRACT

ESTIMATING CO₂ EMISSIONS FROM TILLED SOILS THROUGH ARTIFICIAL NEURAL NETWORKS AND MULTIPLE LINEAR REGRESSION¹

ESTIMATIVAS DE EMISSÃO DE CO₂ EM SOLOS CULTIVADOS POR MEIO DE REDES NEURAIS ARTIFICIAS E MODELO LINEAR DE REGRESSÃO