PA meets Lot - Integrating in-situ Sensor Data and Biomass Prediction Tools for Crops and Pastures

Muhammad Moshiur Rahman; David Lamb; John Stanley; Mark Trotter

PA meets Lot - Integrating in-situ Sensor Data and Biomass Prediction Tools for Crops and Pastures

Muhammad Moshiur Rahman
, David Lamb
, John Stanley
, Mark Trotter

Research output: Contribution to conference › Paper

Abstract

Monitoring pasture growth rate is an important component of managing grazing livestock production systems. In this study we demonstrate a pasture growth rate (PGR) model, initially designed for very large scale satellite imagery, can be operated at a scale of metres when incorporating in-situ sensor data. A light use efficiency (LUE)-based PGR model was combined with in-situ measurements from proximal weather (temperature), plant (fAPAR) and soil (relative moisture) sensors to calculate the growth rate of a tall fescue pasture. When incorporating in-situ measurements of temperature and moisture index, the model provided an accuracy (RMSE) of 1.68 kg/ha.day (R² = 0.96, p-value ≈ 0).

Original language	English
Pages	100-104
Publication status	Published - 31 Dec 2014
Event	Precision Agriculture 2014: 17th Symposium on Precision Agriculture in Australasia - Adelaide, Australia Duration: 2 Sept 2014 → 3 Sept 2014

Conference

Conference	Precision Agriculture 2014: 17th Symposium on Precision Agriculture in Australasia
City	Adelaide, Australia
Period	2/09/14 → 3/09/14

Keywords

Crop and Pasture Production
Agronomy

Access to Document

https://hdl.handle.net/1959.11/20180

Handle.net

Persistent link

Cite this

@conference{003a50abaee94e86bde0b516c8de6514,

title = "PA meets Lot - Integrating in-situ Sensor Data and Biomass Prediction Tools for Crops and Pastures",

abstract = "Monitoring pasture growth rate is an important component of managing grazing livestock production systems. In this study we demonstrate a pasture growth rate (PGR) model, initially designed for very large scale satellite imagery, can be operated at a scale of metres when incorporating in-situ sensor data. A light use efficiency (LUE)-based PGR model was combined with in-situ measurements from proximal weather (temperature), plant (fAPAR) and soil (relative moisture) sensors to calculate the growth rate of a tall fescue pasture. When incorporating in-situ measurements of temperature and moisture index, the model provided an accuracy (RMSE) of 1.68 kg/ha.day (R² = 0.96, p-value ≈ 0).",

keywords = "Crop and Pasture Production, Agronomy",

author = "Rahman, \{Muhammad Moshiur\} and David Lamb and John Stanley and Mark Trotter",

year = "2014",

month = dec,

day = "31",

language = "English",

pages = "100--104",

note = "Precision Agriculture 2014: 17th Symposium on Precision Agriculture in Australasia ; Conference date: 02-09-2014 Through 03-09-2014",

}

TY - CONF

T1 - PA meets Lot - Integrating in-situ Sensor Data and Biomass Prediction Tools for Crops and Pastures

AU - Rahman, Muhammad Moshiur

AU - Lamb, David

AU - Stanley, John

AU - Trotter, Mark

PY - 2014/12/31

Y1 - 2014/12/31

N2 - Monitoring pasture growth rate is an important component of managing grazing livestock production systems. In this study we demonstrate a pasture growth rate (PGR) model, initially designed for very large scale satellite imagery, can be operated at a scale of metres when incorporating in-situ sensor data. A light use efficiency (LUE)-based PGR model was combined with in-situ measurements from proximal weather (temperature), plant (fAPAR) and soil (relative moisture) sensors to calculate the growth rate of a tall fescue pasture. When incorporating in-situ measurements of temperature and moisture index, the model provided an accuracy (RMSE) of 1.68 kg/ha.day (R² = 0.96, p-value ≈ 0).

AB - Monitoring pasture growth rate is an important component of managing grazing livestock production systems. In this study we demonstrate a pasture growth rate (PGR) model, initially designed for very large scale satellite imagery, can be operated at a scale of metres when incorporating in-situ sensor data. A light use efficiency (LUE)-based PGR model was combined with in-situ measurements from proximal weather (temperature), plant (fAPAR) and soil (relative moisture) sensors to calculate the growth rate of a tall fescue pasture. When incorporating in-situ measurements of temperature and moisture index, the model provided an accuracy (RMSE) of 1.68 kg/ha.day (R² = 0.96, p-value ≈ 0).

KW - Crop and Pasture Production

KW - Agronomy

UR - http://sydney.edu.au/agriculture/pal/documents/2014/17th%20PA%20Symposium%20Proceedings.pdf

M3 - Paper

SP - 100

EP - 104

T2 - Precision Agriculture 2014: 17th Symposium on Precision Agriculture in Australasia

Y2 - 2 September 2014 through 3 September 2014

ER -

PA meets Lot - Integrating in-situ Sensor Data and Biomass Prediction Tools for Crops and Pastures

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this