Use of geostatistical analyses for wheat production areas throung the variables NDVI, surface temperature and yield

A.L. Abreu¹, G.A.S. Ferraz¹*, R. Morais¹, N.L. Bento¹, L. Conti³, G. Bambi³ and P.F.P. Ferraz¹

¹Federal University of Lavras - UFLA, School of Engineering, Department of Engineering (EENG/DEA), Aquenta Sol, P.O.Brox 3037, 37200-900 Lavras - MG, Brazil
²University of Florence – UniFI, Department of Agriculture, Food, Environment and Forestry (DAGRI), Via San Bonaventura, 13, 50145 Florence, Italy
*Correspondence:gabriel.ferraz@ufla.br

Abstract:

Geostatistics is a crucial tool for data analysis in the field of precision agriculture, allowing the characterization of spatial variability magnitude, optimizing profitability and yield in agricultural areas. In this context, the present study aimed to evaluate the spatial dependence of the variables yield, Normalized Difference Vegetation Index (NDVI), and surface temperature in winter wheat plants. This was achieved through fitting semivariograms with different statistical models and interpolating the study variables using Ordinary kriging. The experiment was conducted at Fazenda Santa Helena, located in the municipality of Lavras in the state of Minas Gerais, Brazil, with a 12-hectare winter wheat crop of the TBIO Calibre variety. Data were collected using a grid sampling method at different stages of wheat plant growth (tillering and elongation). The analyzed variables included yield, NDVI, and surface temperature. Statistical analyses were performed using the R software. Initially, the spatial dependence of the study variables was analyzed by fitting semivariograms using the Restricted Maximum Likelihood (REML) method and considering spherical, exponential, and gaussian models. The evaluation of errors was carried out through cross-validation, and subsequently, the data interpolation was performed using ordinary kriging with the best-fitted semivariogram model. The results demonstrated a proper fit of semivariograms for the study models, with the spherical model standing out for surface temperature variables (elongation and tillering), NDVI (tillering), and the exponential model for NDVI (elongation) and yield. Therefore, the use of geostatistics is emphasized as an important tool to assist in precision agriculture management in winter wheat crops.

Key words:

active sensor, cross-validation, spatial analyses, vegetation index, winter wheat

Prediction of fruit rot disease incidence in Arecanut based on weather parameters

K. Rajashree¹*, K.V. Prema², G. Rajath³ and S. Angad¹

¹Manipal Academy of Higher Education, Manipal Institute of Technology, Department of Computer Science and Engineering, Madhav Nagar, Manipal, IN576104 Karnataka India
²Manipal Academy of Higher Education, Manipal Institute of Technology, Department of Computer Science and Engineering, BSF Campus, Yelahanka, Bangalore, IN560064 Karnataka, India
³PES University, PES Institute of Technology, Department of Electronics and Communication, Dwaraka Nagar, Banashankari, Bangalore, IN560085 Karnataka, India
*Correspondence: raji.krish@manipal.edu

Abstract:

The occurrence of pests and diseases in arecanut crops has always been an important factor affecting the total production of arecanut. Arecanut is always dependent on environmental factors during its growth. Thus monitoring and early prediction of the occurrence of the disease would be very helpful for prevention and therefore more crop production. Here, we propose artificial intelligence-based deep learning models for fruit rot disease prediction. Historical data on fruit rot incidence in representative areas of arecanut production in Udupi along with historical weather data are the parameters used to develop region-specific models for the Udupi district. The fruit rot disease incidence score value is predicted using recurrent neural network variants (i.e., Vanilla LSTM, Vanilla GRU, stacked LSTM, and Bidirectional LSTM) for the first time. The predictive performance of the proposed models is evaluated by mean square error (MSE) along with the 5-fold cross-validation technique. Further, compared to other deep learning and machine learning models, the Vanilla LSTM model gives 1.5 MSE, while the Vanilla GRU model gives 1.3 MSE making it the best prediction model for arecanut fruit rot disease.

Key words: