Image masking for crop yield forecasting using AVHRR NDVI time series imagery

Kastens, Jude H.; Kastens, Terry L.; Kastens, Dietrich; Price, Kevin P.; Martinko, Edward A.; Lee, Re-Yang

doi:10.1016/j.rse.2005.09.010

Cited by 133 publications

(96 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Maselli and Rembold (2001) and Kastens et al (2005) reported that the correlation map could perform well in regions of sparse crop distribution, such as in the eastern region of our study area, once it can express information on the fractional land cover in a pixel. Our analysis supports the general findings of these previous studies.…”

Section: Correlation Mapsmentioning

confidence: 69%

“…The methods are often based on monthly vegetation indices values (Maselli and Rembold, 2001) or on accumulation over determined periods of the crop phenological stage (Tucker et al, 1980;Rasmussen, 1992;Genovese et al, 2001;Kastens et al, 2005;Ren et al, 2008).…”

Section: Correlation Mapsmentioning

confidence: 99%

“…Kastens et al (2005) used a similar approach by applying masks with different sizes to test its capacity to forecast yield.…”

Section: Regression Modelmentioning

confidence: 99%

“…This may be explained due to regional characteristics, such as irregular terrain and, consequently, smaller cropland areas compared to the western region. Kastens et al (2005) pointed out that the correlation approach would be better applied in these types of areas since there are many difficulties in building crop specific masks with coarse resolution in areas with low production or where cropland areas are interspersed with non-cropland.…”

Section: Estimated Yield: Correlation Maps Versus Crop Specific Masksmentioning

confidence: 99%

“…They reported that areas with low NDVI values could present high correlation due to the presence of grasses with a similar phenology, such as cereals. Combining both the percentage map and the correlation between NDVI and yield, Kastens et al (2005) created the "yield-correlation masking" approach to estimate cereal yield in the United States. The authors found that vegetation in a region can integrate the growing conditions, which could be more indicative of crop potential.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Correlation maps to assess soybean yield from EVI data in Paraná State, Brazil

Figueiredo

Brunsell

Higa

et al. 2016

Sci. agric. (Piracicaba, Braz.)

View full text Add to dashboard Cite

Vegetation indices are widely used to monitor crop development and generally used as input data in models to forecast yield. The first step of this study consisted of using monthly . We compared the ability of forecasting crop yield based on correlation maps and crop specific masks. We ran a preliminary regression model to test its ability on yield estimation for four municipalities during the soybean growing season. A regression model was developed for both methodologies to forecast soybean crop yield using leave-one-out cross validation.The Root Mean Squared Error (RMSE) values in the implementation of the model ranged from 0.037 t ha −1 to 0.19 t ha −1 using correlation maps, while for crop specific masks, it varied from 0.21 t ha −1 to 0.35 t ha −1 . The model was able to explain 96 % to 98 % of the variance in estimated yield from correlation maps, while it was able to explain only 2 % to 67 % for crop specific mask approach. The results showed that the correlation maps could be used to predict crop yield more effectively than crop specific masks. In addition, this method can provide an indication of soybean yield prior to harvesting.

show abstract

Section: Correlation Mapsmentioning

confidence: 69%

Section: Correlation Mapsmentioning

confidence: 99%

“…Kastens et al (2005) used a similar approach by applying masks with different sizes to test its capacity to forecast yield.…”

Section: Regression Modelmentioning

confidence: 99%

Section: Estimated Yield: Correlation Maps Versus Crop Specific Masksmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Correlation maps to assess soybean yield from EVI data in Paraná State, Brazil

Figueiredo

Brunsell

Higa

et al. 2016

Sci. agric. (Piracicaba, Braz.)

View full text Add to dashboard Cite

show abstract

Accuracy, Objectivity and Efficiency of Remote Sensing for Agricultural Statistics

Gallego¹,

Carfagna²,

Baruth³

2010

Agricultural Survey Methods

View full text Add to dashboard Cite

Agricultural statistics in the UN Economic Commission for Europe (UNECE) region are well advanced. Information collected by farm structure surveys on the characteristics of farms, farmers' households and holdings is for example combined with a variety of information on the production of animal products, crops, etc. Agricultural accounts are produced on a regular basis and a large variety of indicators on agri-economic issues is available. At the level of the European Union as a whole the harmonization-forced by a stringent regulatory framework-of the collection, validation and analysis of agricultural information has led to a settled system of statistics. Recent developments in methodologies for data collection (e.g. using hand-held computers, registers and administrative sources, advanced sampling techniques and remote sensing) are shaking up the development of agricultural statistics. There is a lack of uniformity in the pace at which different countries in the UNECE region are introducing new methodologies and techniques. The need to reduce the burden on farmers and to organize the collection and analysis of data more efficiently creates a set of challenges for the countries.

show abstract

Rice straw biochar and irrigation effect on yield and water productivity of okra

et al. 2020

View full text Add to dashboard Cite

Dry season vegetable production is challenging due to water scarcity, a drawback on sustaining year‐round crop production. Biochar improves soil moisture and nutrient retention and may be used to improve vegetable water productivity. We examined the combined effect of rice straw biochar and irrigation on yield, water productivity, and phosphorus (P) uptake of okra (Abelmoschus esculentus L.) grown on a sandy clay loam soil in the dry season. Biochar was applied at 0, 5, 10 Mg ha−1, and 10 Mg ha−1 biochar fortified with P [10 Mg ha−1(P)] under full irrigation (FI) and deficit irrigation (DI) and replicated in each growing season for three years. Under DI, the 10 Mg ha−1 and 10 Mg ha−1(P) biochar treatments significantly (p < .05) increased okra fresh fruit yield (YFF) by 67 and 82% but had no impact on total aboveground biomass yield (YTBM) in the first growing season. Biochar at 5 Mg ha−1 had no impact on okra yield. Okra yield was higher under biochar fortified with P compared to the traditional method of applying P alone, e.g. 30 Mg ha−1(P) produced significantly higher YTBM than 30 Mg ha−1 under DI. Biochar had no impact on P uptake in the first growing season. Estimated okra water use was 224 and 193 mm under FI and DI. Yield reduction under DI compared to FI was only 8%. Amid water scarcity, a minimum of 10 Mg ha−1 rice straw biochar under DI is therefore recommended for farmers in the area.

show abstract

Image masking for crop yield forecasting using AVHRR NDVI time series imagery

Cited by 133 publications

References 24 publications

Correlation maps to assess soybean yield from EVI data in Paraná State, Brazil

Correlation maps to assess soybean yield from EVI data in Paraná State, Brazil

Accuracy, Objectivity and Efficiency of Remote Sensing for Agricultural Statistics

Rice straw biochar and irrigation effect on yield and water productivity of okra

Contact Info

Product

Resources

About