Peanut Loss Predictions Using Random Forest and Soil Data

• Armando L. de Brito Filho Unesp
• Franciele M. Carneiro UTFPR
• Gabriel P. Costa Unesp
• Lucas Matheus Agostini Unesp
• Jarlyson Brunno Costa Souza Unesp
• Rouverson P. da Silva Unesp

DOI: https://doi.org/10.5753/sbiagro.2023.26543

Resumo

This work aimed to evaluate the Random Forest algorithm performance to predict mechanical digging loss of the peanut crop. Four approaches were tested: only soil texture data, soil texture + TPI, soil texture + TWI, and soil texture + TPI + TWI. The model's performance was evaluated regarding precision (coefficient of determination) and accuracy (mean absolute error). The results found in this work proved promising in predicting peanut digging losses. Our models achieve results with an approximate 100 kg ha-1 prediction error. In addition, incorporating one or more topographical indexes in conjunction with soil texture data as features notably improves the models' precision and accuracy.

Referências

Behera, B. K., Behera, D., Mohapatra, A. K., Swain, S., Goel, A. K. (2008) Performance evaluation of a Bullock drawn groundnut digger. Environment and Ecology, v.26, p.1226-1229.

Ince, A. and Guzel E. (2003). Effects of gynophore breaking resistance on losses in mechanized peanut harvesting. In: International conference on crop harvesting and processing, Louisville, Kentucky. ProceedingsÉ St Joseph: ASABE. 2003. p. 1103.

Jeong, J. H., Resop, J. P., Mueller, N. D., Fleisher, D. H., Yun, K., Butler, E. E., Kim, S. H. (2016). Random forests for global and regional crop yield predictions. PloS one, 11(6), e0156571

Oliveira, R. P., Barbosa Júnior, M. R., Pinto, A. A., Oliveira, J. L. P., Zerbato, C., Furlani, C. E. A. (2022). Predicting sugarcane biometric parameters by UAV multispectral images and machine learning. Agronomy, 12(9), 1992.

Santos, A. F., Silva, R. P., Zerbato, C., Menezes, P. C., Kazama, E. H., Paixão, C. S. S., Voltarelli, M. A. (2019). Use of real- time extend GNSS for planting and inverting peanuts. Precis. Agric. 2019, 20, 840–856.

Silva, R. P. (2019). Colheita mecanizada de amendoim. In: Silva R. P.; Santos A. F.; Carrega W. C. (Eds.) Avanços na produção de amendoim. Jaboticabal: FUNEP, p. 129–141.

Yang, M., Wang, G., Lazin, R., Shen, X., Anagnostou, E. (2021) Impact of planting time soil moisture on cereal crop yield in the Upper Blue Nile Basin: A novel insight towards agricultural water management. Agricultural Water Management, v. 243, n. February 2020, p. 106430.

Yue, J., Yang, G., Tian, Q., Feng, H., Xu, K., Zhou, C. (2019). Estimate of winter-wheat above-ground biomass based on UAV ultrahigh-ground-resolution image textures and vegetation indices. ISPRS Journal of Photogrammetry and Remote Sensing 150:226–244.

Zerbato, C., Furlani, C. E. A., Silva, R. P., Voltarelli, M. A., Santos, A. F. (2017). Statistical control of processes aplied for peanut mechanical digging in soil te xtural classes. Engenharia Agrícola, 37(2), 315-322.

Zerbato, C., Furlani, C. E. A., Oliveira M. F. D., Voltarelli, M. A., Tavares, T. O., Carneiro, F. M. (2019). Quality of mechanical peanut sowing and digging using autopilot. Revista Brasileira de Engenharia Agrícola e Ambiental, v. 23, n. 8, p. 630-637.

Zerbato, C., Silva, V. F., Torres, L. S., Silva, R. P. D., Furlani, C. E. (2014). Peanut mechanized digging regarding to plant population and soil water level. Revista Brasileira de Engenharia Agrícola e Ambiental, 18, 459-465.