Clustering analysis applied to NDVI/NOAA multitemporal images to improve the monitoring process of sugarcane crops

Romani, L. A. S.; Gonçalves, Renata Ribeiro do Valle; Amaral, Bruno Ferraz do; Chino, Daniel Yoshinobu Takada; Zullo, Jurandir; Traina, Caetano; Sousa, Elaine Parros Machado de; Traina, Agma J. M.

doi:10.1109/multi-temp.2011.6005040

Cited by 14 publications

(12 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For sugarcane, satellite observation has more traditionally been used for applications such as classifying different sugarcane varieties using spectral indices [3,4]. The analysis of temporal series has also been used to classify and separate sugarcane clusters from the rest of land use/land cover classes, aiding the assessment of sugarcane expansion in the Sã o Paulo region [5][6][7]. Within this framework, the Canasat Project [5], developed by INPE (Instituto Nacional de Pesquisas Espaciais, Brazil), is producing sugarcane distribution maps.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Processing of 1-km Spatial Resolution fAPAR Time Series for Sugarcane Yield Forecasting and Monitoring

2013

View full text Add to dashboard Cite

A processing of remotely-sensed Fraction of Absorbed Photosynthetically Active Radiation (fAPAR) time series at 1-km spatial resolution is established to estimate sugarcane yield over the state of Sã o Paulo, Brazil. It includes selecting adequate time series according to the signal spatial purity, using thermal time instead of calendar time and smoothing temporally the irregularly sampled observations. A systematic construction of various metrics and their capacity to predict yield is explored to identify the best performance, and see how timely the yield forecast can be made. The resulting dataset not only reveals a strong spatio-temporal structure, but is also capable of detecting both absolute changes in biomass accumulation and changes in its inter-annual variability. Sugarcane yield can thus be estimated with a RMSE of 1.5 t/ha (or 2%) without taking into account the strong linear trend in yield increase witnessed in the past decade. Including the trend reduces the error to 0.6 t/ha, correctly predicting whether the yield in a given year is above or below the trend in 90% of cases. The methodological framework presented here could be applied beyond the specific case of sugarcane in Sã o Paulo, namely to other crops in other agro-ecological landscapes, to enhance current systems for monitoring agriculture or forecasting yield using remote sensing.

show abstract

Section: Introductionmentioning

confidence: 99%

Enhanced Processing of 1-km Spatial Resolution fAPAR Time Series for Sugarcane Yield Forecasting and Monitoring

2013

View full text Add to dashboard Cite

show abstract

“…Based on a time series of pixel-based (raster) images, time profile clustering is a method that compares the time profiles of all pixels and distributes them among a limited number of "typical" behaviors (classes) that can be mapped [58][59][60]. Profiles of NDVI and VHI departure from the average of the last five or twelve years are clustered in CropWatch for MPZs, countries and subdivisions of large countries.…”

Section: Crop Condition Indicatorsmentioning

confidence: 99%

Global Crop Monitoring: A Satellite-Based Hierarchical Approach

Gommes

Zhang

et al. 2015

Remote Sensing

View full text Add to dashboard Cite

Taking advantage of multiple new remote sensing data sources, especially from Chinese satellites, the CropWatch system has expanded the scope of its international analyses through the development of new indicators and an upgraded operational methodology. The approach adopts a hierarchical system covering four spatial levels of detail: global, regional, national (thirty-one key countries including China) and "sub-countries" (for the nine largest countries). The thirty-one countries encompass more that 80% of both production and exports of maize, rice, soybean and wheat. The methodology resorts to climatic and remote sensing indicators at different scales. The global patterns of crop environmental growing conditions are first analyzed with indicators for rainfall, temperature, photosynthetically active radiation (PAR) as well as potential biomass. At the regional scale, the indicators pay more attention to crops and include Vegetation Health Index (VHI), Vegetation Condition Index (VCI), Cropped Arable Land Fraction (CALF) as well as Cropping Intensity (CI). Together, they characterize crop situation, farming intensity and stress. CropWatch carries out detailed crop condition analyses at the national scale with a comprehensive array of variables and indicators. The Normalized Difference Vegetation Index (NDVI), cropped areas and crop conditions are integrated to derive food production estimates. For the nine OPEN ACCESSRemote Sens. 2015, 7 3908 largest countries, CropWatch zooms into the sub-national units to acquire detailed information on crop condition and production by including new indicators (e.g., Crop type proportion). Based on trend analysis, CropWatch also issues crop production supply outlooks, covering both long-term variations and short-term dynamic changes in key food exporters and importers. The hierarchical approach adopted by CropWatch is the basis of the analyses of climatic and crop conditions assessments published in the quarterly "CropWatch bulletin" which provides accurate and timely information essential to food producers, traders and consumers.

show abstract

“…A good amount of work has been reported in the area of Remote Sensing and GIS on the application of k-medoids to solve various problems such as spatial data clustering, indexing spatial data, change detection, NDVI calculations [6][7] [8], etc. Although an implementation of k-medoids for large data sets is available (e.g.…”

Section: Need For Gpu Driven Clustering Algorithmsmentioning

confidence: 99%

High resolution disaster data clustering using Graphics Processing Units

Kurte

Durbha

2013

2013 IEEE International Geoscience and Remote Sensing Symposium - IGARSS

View full text Add to dashboard Cite

Near real time processing and clusters extraction from high-resolution satellite images of disaster affected area aids in monitoring and deployment of rescue activities. In this work the k-medoids clustering algorithm is analyzed for near real time applications. In general, due to the large size of satellite data, the computational time of traditional k-medoids is found to be very high. Hence in order to achieve the aim of near real time processing of such huge data we developed a parallel implementation of k-medoids (GPUPAM) and integrated with CLARA (Clustering for LARge Application), which is one of the variant of kmedoids. The implementation is performed on NVIDIA's Graphical Processing Unit (GPU).The performance improvements that were obtained is demonstrated by a GPU implementation on high resolution Haiti Earthquake QuickBird (2.4 meter resolution) data and compared with the traditional sequential implementation. The results show that the GPU implementation is found to achieve almost 96% performance improvement as compared to the sequential implementation.

show abstract

Clustering analysis applied to NDVI/NOAA multitemporal images to improve the monitoring process of sugarcane crops

Cited by 14 publications

References 3 publications

Enhanced Processing of 1-km Spatial Resolution fAPAR Time Series for Sugarcane Yield Forecasting and Monitoring

Enhanced Processing of 1-km Spatial Resolution fAPAR Time Series for Sugarcane Yield Forecasting and Monitoring

Global Crop Monitoring: A Satellite-Based Hierarchical Approach

High resolution disaster data clustering using Graphics Processing Units

Contact Info

Product

Resources

About