Soil Urea Estimation using Embedded Systems
Sulaxana R.Vernekar1, Jivan S. Parab2
1Sulaxana R. Vernekar, Assistant Professor, Department of Computer Science at GVM‟s GGPR College of Commerce, Ponda-Goa.
2Jivan S. Parab, Assistant Professor, Department of Electronics, Goa University.

Manuscript received on November 11, 2019. | Revised Manuscript received on November 20 2019. | Manuscript published on 30 November, 2019. | PP: 11296-11299 | Volume-8 Issue-4, November 2019. | Retrieval Number: D9565118419/2019©BEIESP | DOI: 10.35940/ijrte.D9565.118419

Open Access | Ethics and Policies | Cite  | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: With the advancements in technology constant efforts are being made towards making agriculture sustainable. Green Revolution made extensive use of chemical fertilizers to increase the crop yield, which gave the desired outputs, but high usage of fertilizers led to soil degradability, ground water contamination etc. Precision farming techniques are currently being used to make agriculture sustainable and profitable. Lot of automation is involved in the techniques used for irrigation, harvesting, soil testing etc. Soil testing is an important aspect in agriculture as it decides the crops that can be grown in a particular type of soil and also todecide how much external inputs can be applied to give a good crop yield. Precision farming involves techniques which are real time based. The paper discusses the design and development of a novel soft core embedded platform on Altera FPGA for estimation of urea in soil. RF spectra of five different constituents found in soil are recorded using a scalar network analyzer consisting of Signal Hound tracking generator TG44A and Signal Hound spectrum analyzerUSB-SA124B and a dielectric cell. The samples for recording the RF spectra are prepared in the laboratory by mixing five different constituents namely urea, potash, phoshate, salt and lime taken in the study in distilled water in different proportions. The spectra obtained are then passed through a multivariate system ported on FPGA for the estimation of an unknown concentration of urea in a sample. The multivariate analysis is done using Partial Least Square Regression (PLSR) technique and is implemented using SIMPLS algorithm developed in C. The results obtained show that the estimated values of urea have percentage error of around 5% which is acceptable. Even if the sample concentrations lie outside the confidence interval i.e CI, the estimated results are still satisfactory.
Keywords: Multivariate, FPGA, PLSR, RF Spectroscopy, Urea.
Scope of the Article: Cyber Physical Systems (CPS).