Estimation of dynamic parameters of MODIS NDVI time series nonlinear model using particle filtering

Srija Chakraborty; Ayan Banerjee; Sandeep Gupta; Antonia Papandreou-Suppappola; Philip Christensen

doi:10.1109/IGARSS.2017.8127146

Estimation of dynamic parameters of MODIS NDVI time series nonlinear model using particle filtering

Srija Chakraborty, Ayan Banerjee, Sandeep Gupta, Antonia Papandreou-Suppappola, Philip Christensen

Earth and Space Exploration, School of (SESE)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Scopus citations

Abstract

Normalized Difference Vegetation Index (NDVI) time series is used to study different land cover dynamics such as change, compare vegetation dynamics between years and analyze intra-annual components. A nonlinear cosine model of the NDVI time series with a constant frequency is used to account for the time-varying nature of the land cover parameters due to seasonality or change. The Extended Kalman Filter (EKF) is used to estimate these parameters, which introduces linearization and negatively impacts the state estimation accuracy. This paper proposes using a Particle Filter (PF) for state estimation to better address nonlinearity in the model. The cosine model is modified to capture frequency variations to account for changes in the vegetation growth cycle caused by abrupt phenomenon such as forest fires. PF obtains better state estimates than EKF, capturing the intra-annual components and time-varying frequency of the model accurately.

Original language	English (US)
Title of host publication	2017 IEEE International Geoscience and Remote Sensing Symposium
Subtitle of host publication	International Cooperation for Global Awareness, IGARSS 2017 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1091-1094
Number of pages	4
Volume	2017-July
ISBN (Electronic)	9781509049516
DOIs	https://doi.org/10.1109/IGARSS.2017.8127146
State	Published - Dec 1 2017
Event	37th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2017 - Fort Worth, United States Duration: Jul 23 2017 → Jul 28 2017

Other

Other	37th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2017
Country/Territory	United States
City	Fort Worth
Period	7/23/17 → 7/28/17

Keywords

Land cover change detection
nonlinear model
particle filter

ASJC Scopus subject areas

Computer Science Applications
General Earth and Planetary Sciences

Access to Document

10.1109/IGARSS.2017.8127146

Cite this

Chakraborty, S., Banerjee, A., Gupta, S., Papandreou-Suppappola, A., & Christensen, P. (2017). Estimation of dynamic parameters of MODIS NDVI time series nonlinear model using particle filtering. In 2017 IEEE International Geoscience and Remote Sensing Symposium: International Cooperation for Global Awareness, IGARSS 2017 - Proceedings (Vol. 2017-July, pp. 1091-1094). Article 8127146 Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2017.8127146

Estimation of dynamic parameters of MODIS NDVI time series nonlinear model using particle filtering. / Chakraborty, Srija; Banerjee, Ayan ; Gupta, Sandeep et al.
2017 IEEE International Geoscience and Remote Sensing Symposium: International Cooperation for Global Awareness, IGARSS 2017 - Proceedings. Vol. 2017-July Institute of Electrical and Electronics Engineers Inc., 2017. p. 1091-1094 8127146.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Chakraborty, S, Banerjee, A , Gupta, S , Papandreou-Suppappola, A & Christensen, P 2017, Estimation of dynamic parameters of MODIS NDVI time series nonlinear model using particle filtering. in 2017 IEEE International Geoscience and Remote Sensing Symposium: International Cooperation for Global Awareness, IGARSS 2017 - Proceedings. vol. 2017-July, 8127146, Institute of Electrical and Electronics Engineers Inc., pp. 1091-1094, 37th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2017, Fort Worth, United States, 7/23/17. https://doi.org/10.1109/IGARSS.2017.8127146

Chakraborty S, Banerjee A , Gupta S , Papandreou-Suppappola A , Christensen P. Estimation of dynamic parameters of MODIS NDVI time series nonlinear model using particle filtering. In 2017 IEEE International Geoscience and Remote Sensing Symposium: International Cooperation for Global Awareness, IGARSS 2017 - Proceedings. Vol. 2017-July. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1091-1094. 8127146 doi: 10.1109/IGARSS.2017.8127146

Chakraborty, Srija ; Banerjee, Ayan ; Gupta, Sandeep et al. / Estimation of dynamic parameters of MODIS NDVI time series nonlinear model using particle filtering. 2017 IEEE International Geoscience and Remote Sensing Symposium: International Cooperation for Global Awareness, IGARSS 2017 - Proceedings. Vol. 2017-July Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1091-1094

@inproceedings{d4e6325cb7e648e68cc9d8b6c9396a68,

title = "Estimation of dynamic parameters of MODIS NDVI time series nonlinear model using particle filtering",

abstract = "Normalized Difference Vegetation Index (NDVI) time series is used to study different land cover dynamics such as change, compare vegetation dynamics between years and analyze intra-annual components. A nonlinear cosine model of the NDVI time series with a constant frequency is used to account for the time-varying nature of the land cover parameters due to seasonality or change. The Extended Kalman Filter (EKF) is used to estimate these parameters, which introduces linearization and negatively impacts the state estimation accuracy. This paper proposes using a Particle Filter (PF) for state estimation to better address nonlinearity in the model. The cosine model is modified to capture frequency variations to account for changes in the vegetation growth cycle caused by abrupt phenomenon such as forest fires. PF obtains better state estimates than EKF, capturing the intra-annual components and time-varying frequency of the model accurately.",

keywords = "Land cover change detection, nonlinear model, particle filter",

author = "Srija Chakraborty and Ayan Banerjee and Sandeep Gupta and Antonia Papandreou-Suppappola and Philip Christensen",

year = "2017",

month = dec,

day = "1",

doi = "10.1109/IGARSS.2017.8127146",

language = "English (US)",

volume = "2017-July",

pages = "1091--1094",

booktitle = "2017 IEEE International Geoscience and Remote Sensing Symposium",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "37th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2017 ; Conference date: 23-07-2017 Through 28-07-2017",

}

TY - GEN

T1 - Estimation of dynamic parameters of MODIS NDVI time series nonlinear model using particle filtering

AU - Chakraborty, Srija

AU - Banerjee, Ayan

AU - Gupta, Sandeep

AU - Papandreou-Suppappola, Antonia

AU - Christensen, Philip

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Normalized Difference Vegetation Index (NDVI) time series is used to study different land cover dynamics such as change, compare vegetation dynamics between years and analyze intra-annual components. A nonlinear cosine model of the NDVI time series with a constant frequency is used to account for the time-varying nature of the land cover parameters due to seasonality or change. The Extended Kalman Filter (EKF) is used to estimate these parameters, which introduces linearization and negatively impacts the state estimation accuracy. This paper proposes using a Particle Filter (PF) for state estimation to better address nonlinearity in the model. The cosine model is modified to capture frequency variations to account for changes in the vegetation growth cycle caused by abrupt phenomenon such as forest fires. PF obtains better state estimates than EKF, capturing the intra-annual components and time-varying frequency of the model accurately.

AB - Normalized Difference Vegetation Index (NDVI) time series is used to study different land cover dynamics such as change, compare vegetation dynamics between years and analyze intra-annual components. A nonlinear cosine model of the NDVI time series with a constant frequency is used to account for the time-varying nature of the land cover parameters due to seasonality or change. The Extended Kalman Filter (EKF) is used to estimate these parameters, which introduces linearization and negatively impacts the state estimation accuracy. This paper proposes using a Particle Filter (PF) for state estimation to better address nonlinearity in the model. The cosine model is modified to capture frequency variations to account for changes in the vegetation growth cycle caused by abrupt phenomenon such as forest fires. PF obtains better state estimates than EKF, capturing the intra-annual components and time-varying frequency of the model accurately.

KW - Land cover change detection

KW - nonlinear model

KW - particle filter

UR - http://www.scopus.com/inward/record.url?scp=85041853395&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041853395&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2017.8127146

DO - 10.1109/IGARSS.2017.8127146

M3 - Conference contribution

AN - SCOPUS:85041853395

VL - 2017-July

SP - 1091

EP - 1094

BT - 2017 IEEE International Geoscience and Remote Sensing Symposium

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 37th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2017

Y2 - 23 July 2017 through 28 July 2017

ER -

Estimation of dynamic parameters of MODIS NDVI time series nonlinear model using particle filtering

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this