|
area,
and several companies have been developing variable rate
application equipment in recent years. Till now we have not used
this technique in our country. India has remained as one of the
largest contributor of rice, cotton and wheat. However, these
crops have also resulted in the fragile eco-system characterized
in terms of increased pests and crop diseases, depletion of
natural resources particularly ground water and overall living
environment. Proper monitoring and modeling of weather
parameters can help in forecasting the disease and pest outbreak
for taking management action in advance. Similarly, soil
moisture monitoring at spatial scale in contrast to traditional
point based measurement can also lead towards proper amount of
water utilization thereby checking the large scale depletion of
ground water. Fundamentally, Precision Agriculture aims at a dis-aggregated
micro-level farm management strategy with intense information
inputs addressing the variations of soils, crops, water,
chemicals etc. Taking into the present state of Agriculture in
the country, Precision Agriculture is absolutely essential in
order to address poverty alleviation and food security to a very
large cross-section of the population.
The Knowledge of spatial variability of soil attributes within
an agricultural field is critical for successful site-specific
crop management. Soil sensing techniques to assess this
variability on the go are being developed as an alternative to
tedious manual soil sampling and laboratory testing.
The potential of precision agriculture is limited by the lack of
appropriate measurement and analysis techniques for agronomically important factors.
While the concept of precision farming is sound, our understanding of the
physical and biological aspects of the cropping system is incomplete due to
limitations in the current sensing and data processing technologies.
Obtaining and analyzing data are the bottlenecks in the traditional system.
The cost of obtaining information through traditional means e.g. sampling
for soil fertility or pest presence is expensive and time consuming and data
collection is usually conducted in a sparse manner.
The challenges in machine vision specific to the food and agricultural
sectors include the requirements of high speed, variable product
shape and surface inconsistency. Object identification such as
plants has not been developed to as great extent in agriculture
as in other industries, due primarily to the complexity of plant
images. Machine vision technique offers a convenient and
non-destructive way for measurements of soil and plant
characteristics. Recent developments of microprocessor based
image processing system have boosted wider applications of this
technique.
Soil sampling for fertility requirements and variable rate application
requires a tremendous amount of labor, time, and money.
Depending on the grid size, grid soil sampling generates a
tremendous amount of data. In addition, the grid size (or sample
frequency) cannot be adjusted while sampling. If samples could
be analyzed real-time, than grid sizes could be adjusted to
produce a smart sampling scheme. For grid soil sampling to
become better utilized the cost and labor must be decreased. A
number of sensing technologies are available that could produce
acceptable accuracies at a low-cost and near real-time.
Near-infrared reflectance spectroscopy (NIRS)
is one tool that is frequently used for the chemical analysis of numerous
products. NIRS works by shining light at a given wavelength on a material in
question, and measuring the intensity of the reflectance. The reflectance at
certain wavelengths is correlated to specific chemical components.
Developing correlations for materials requires known values of important
properties from a laboratory. The reflectance is measured from each sample
and statistical procedures are used to develop correlations between
reflectance and the data obtained from soil analysis laboratories.
Traditionally, NIRS instruments were very fragile and were confined to use
in a laboratory. Recently, more rugged mobile instruments have been
developed.
Monitoring plant growth is a basic agricultural practice
required to reveal disorders caused by deficiency, toxicity,
pollution, disease or mechanical damage. Research in precision
agriculture has shown the high degree of spatial variability and
the need for the on the go soil and plant sensors to quantify
the variability in a cost effective manner. The
spectrophotometer is one sensor and may have utility in
precision agriculture by measuring diffuse reflectance in the
near infrared spectral (NIR) region. A subset of the
spectra are matched with the results of laboratory analysis and used to
create a calibration using multivariate statistical techniques. If the
radiation arriving at the sensor is measured at each wavelength over a
sufficiently broad spectral band the resulting spectral signature can be
used to uniquely characterize and identify any given material. In this
sense, hyper spectral images are fundamental for the investigation of the
world by vision. This study is aimed to determine the important properties
of soil and plant by using reflectance spectra for the Indian fields. The
objective of this investigation is to develop relationships between
different properties of soil & plant and wavelength of their reflectance
bands for the quantification of these parameters. The yield monitor is
intended to give the user an accurate assessment of how yields vary within a
field. Although a yield monitor can assist grain producers in many aspects
of crop management, the device was never intended to replace scales for
marketing grain.
A yield monitor by itself can provide useful information and
enhance on-farm research. Yield data can be accumulated for a
specific load or field, thereby facilitating the comparison of
hybrids, varieties, or treatments within test plots. For
example, all yield monitors can measure grain mass and harvested
area on a load-by-load or field-by-field basis. This feature
allows an operator to get instantaneous readout in the field of
accumulated grain weight, harvested area, and average yield.
With many yield monitors, these values can be exported to a
personal computer and stored in nonvolatile memory for further
analysis or printing via specialized software packages or more
standard word-processing and spreadsheet software. Season
summaries of harvested areas might then be used to settle custom
harvesting charges or to keep track of production from
individual fields when it is impractical to scale grain trucks.
With a yield monitor, a producer also can conduct on-farm
variety trials or weed control evaluations without the need of a
weigh wagon. Such on-farm comparisons help producers fine-tune
crop production practices to their soils.
Differential Global Positioning System (DGPS) is an integration of space-
and ground-based segments that together comprise a radio-navigation
facility. Initially developed for national security interests, a portion of
the DGPS system is available to civilian users. When yield data are used
with information generated by a DGPS receiver, a producer can generate yield
maps that provide a quick visualization of crop performance within a
particular crop production unit. Ultimately, any increased profit realized
from incorporating a yield monitor into an operation will come from changes
in management practices that result from the identification of problem areas
using such yield maps. With DGPS, the benefits of using a yield monitor are
even more evident.
Sensors use reflected light at two or more wavelengths as proxy variables
for vegetative biomass, plant nutrient status, and indicators of crop health
and yield. Some sensors have been bundled with variable rate application
equipment and are commercially available. The GreenSeeker® (NTech
Industries), Hydro N-Sensor (Yara International ASA), Veris EC sensor are
some examples of sensors marketed specifically for precise real-time
measurements of plant and soil properties. The expense of these specialized
sensors could be better justified if new applications could be identified.
One of the major objectives of precision farming is to vary the rate of
application of field inputs (seeds, fertilizer, lime, herbicides, etc.) in
accordance with site-specific recommendations. While equipment for some
variable-rate field operations is commercially available in developed
countries, there is a need to adapt and assess the methodology and
equipment, as well as to develop new variable-rate technologies for Indian
farms.
Good Precision Agriculture (PA) management decisions cannot be
accomplished without accurate spatial data. The primary tools
that most producers use to gather spatial data are intensive
soil sampling and yield monitoring. Remote sensing (RS) is a
technology that has received much attention recently. The
technical definition of RS is any sensor that can measure some
quantity remotely or without coming in contact with it. In
agriculture, most people understand RS to be crop imagery
obtained from satellites or aerial vehicles. A less common but
very important variation of RS is closer range sensing as in a
land vehicle-mounted sensor. RS is a very desirable sensing
technique for several reasons. A sensor located at one point in
time and space can instantaneously obtain data from a wide area,
which eliminates the need for extensive human sampling and
measurement. RS is a non-contact technique, which means that the
crop is not disturbed or damaged in any way. Some RS equipment,
such as near-infrared (NIR) cameras, can measure
quantities that cannot be seen or observed by a human. There are two issues
regarding the remote sensing, whether the traditional physical and chemical
analysis is substituted by remote sensing methodology and a sensor located
800 km from the target be utilized for parameters quantification. It is
required that new sensing technologies are developed to evaluate and
validate remote sensing for field variability identifications. A general
purpose ground based sensing system to collect high density ground truth
data for the site specific validation of remote sensing as a field
characteristic mapping tool for major crop production is not available.
Problem is solved if, soil/plant attributes by laboratory sensors i.e.
spectroscopy can be correlated with traditional physical and chemical
analysis as well as with satellite remote sensing data. Essentially the
process would involve relating ground information with the satellite using
the spectroradiometer to relate ground gathered data with the satellite. |
