Article
Intelligent Spectroscopy System Used for
Physicochemical Variables Estimation in Sugar
Cane Soils
Ofelia Landeta-Escamilla
1
, Oscar Sandoval-Gonzalez
1
, Albino Martínez-Sibaja
1,
*,
José de Jesús Agustín Flores-Cuautle
2
, Rubén Posada-Gómez
1
and
Alejandro Alvarado-Lassman
1
1
Tecnológico Nacional de Mexico/I.T.Orizaba, Orizaba, VZ 94320, Mexico; of_elia@hotmail.com (O.L.-E.);
o.sandovalgonzalez@gmail.com (O.S.-G.); pgruben@yahoo.com (R.P.-G.); lassman@prodigy.net.mx (A.A.-L.)
2
CONACYT-Tecnológico Nacional de Mexico/I.T.Orizaba, Orizaba, VZ 94320, Mexico;
jflores_cuautle@hotmail.com
* Correspondence: cei.depi.ito@gmail.com; Tel.: +52-272-7033-425
Received: 27 October 2018; Accepted: 27 December 2018; Published: 10 January 2019
Abstract:
The current condition of soils is a major area of interest due to the lack of certainty in their
physicochemical properties, which can guarantee the quality and the production of a specific crop.
Additionally, methodologies to improve land management must be implemented in order to address
the consequences of many environmental issues. To date, many techniques have been implemented
to improve the accuracy—and more recently the speed—of analysis, in order to obtain results while
in the field. Among those, Near Infrared (NIR) spectroscopy has been widely used to achieve the
objectives mentioned above. Nevertheless, it requires particular knowledge, and the cost might be
high for farmers who own the fields and crops. Thus, the present work uses a system that implements
capacitance spectroscopy plus artificial intelligence algorithms to estimate the physicochemical
variables of soil used to grow sugar cane. The device uses the frequency response of the soil to
determine its magnitude and phase values, which are used by artificial intelligence algorithms that
are capable of estimating the soil properties. The obtained results show errors below 8% in the
estimation of the variables compared to the analysis results of the soil in laboratories. Additionally,
it is a portable system, with low cost, that is easy to use and could be implemented to test other types
of soils after evaluating the necessary algorithms or proposing alternatives to restore soil properties.
Keywords: psychochemical prediction; frequency response of soil; FPGA-based
1. Introduction
A global issue to attend due to its relevancy is soil degradation: firstly, because it is a
natural resource that is formed and regenerated slowly, is not renewable, and is very fragile in
its degradation [
1
]. Therefore, it is one of the most vulnerable natural resources, because it is not
possible to take actions to avoid or mitigate the adverse impacts that are produced by environmental
detriment [
2
]. Soil plays a crucial role in the functioning of ecosystems [
3
] due to the impact on
agronomics and food security [
4
], by decreasing its current and potential capability to produce goods
and services. Land management is far from being sustainable; there has been an inadequate operation
of soils in the conventional production systems [
5
]. For example, the excessive use of fertilizers has
led to nitrogen depositions affecting not only surface and underground water, but also soils with
acidification, because an incorrect application of modern agrotechnologies [
6
] generates unstable
ecosystems, which in turn creates an external dependence on energy and materials for their continuity
in time [
7
]. In turn, this increases the number of limiting factors in the production systems in relation
Sensors 2019, 19, 240; doi:10.3390/s19010240 www.mdpi.com/journal/sensors
