A comparison of global agricultural monitoring systems and current gaps

Fritz, Steffen; Bayas, Juan Carlos Laso; Waldner, François; Jacques, Denis; Becker‐Reshef, Inbal; Whitcraft, A. K.; Baruth, Bettina; Bonifácio, Rogério; Crutchfield, Jim; Rembold, Felix; Rojas, Oscar; Schucknecht, Anne; Velde, Marijn van der; Verdin, J. P.; Wu, Bingfang; Niu, Y.; You, Liangzhi; Gilliams, Sven; Mücher, Sander; Tetrault, Robert; Moorthy, Inian; McCallum, Ian

doi:10.1016/j.agsy.2018.05.010

Cited by 210 publications

(117 citation statements)

References 59 publications

Supporting

Mentioning

112

Contrasting

Unclassified

Order By: Relevance

“…For each classification scheme, the overall accuracy (OA) and Cohen's kappa coefficient of agreement (κ) [65] were calculated as the classifier performance estimators. The OA was defined as OA = ∑ correct predictions total number o f predictions (2) where predictions were calculated for all available validation samples and the predicted labels were compared to the true labels. Similarly, κ was defined as…”

Section: Classification Schemesmentioning

confidence: 99%

“…One of the requirements for ensuring food security is a timely inventory of agricultural areas and the regional proportion of different crop types [1]. Next to the public sector, the private sector, including the agro-and insurance industries, benefit as well from early season crop inventories as an important component of crop production estimation and agricultural statistics [2,3]. In addition to regional estimates, early crop type information at the parcel level is also an essential prerequisite for any crop monitoring activity that aims at early anomaly detection.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Synergistic Use of Radar Sentinel-1 and Optical Sentinel-2 Imagery for Crop Mapping: A Case Study for Belgium

et al. 2018

Self Cite

View full text Add to dashboard Cite

A timely inventory of agricultural areas and crop types is an essential requirement for ensuring global food security and allowing early crop monitoring practices. Satellite remote sensing has proven to be an increasingly more reliable tool to identify crop types. With the Copernicus program and its Sentinel satellites, a growing source of satellite remote sensing data is publicly available at no charge. Here, we used joint Sentinel-1 radar and Sentinel-2 optical imagery to create a crop map for Belgium. To ensure homogenous radar and optical inputs across the country, Sentinel-1 12-day backscatter mosaics were created after incidence angle normalization, and Sentinel-2 normalized difference vegetation index (NDVI) images were smoothed to yield 10-daily cloud-free mosaics. An optimized random forest classifier predicted the eight crop types with a maximum accuracy of 82% and a kappa coefficient of 0.77. We found that a combination of radar and optical imagery always outperformed a classification based on single-sensor inputs, and that classification performance increased throughout the season until July, when differences between crop types were largest. Furthermore, we showed that the concept of classification confidence derived from the random forest classifier provided insight into the reliability of the predicted class for each pixel, clearly showing that parcel borders have a lower classification confidence. We concluded that the synergistic use of radar and optical data for crop classification led to richer information increasing classification accuracies compared to optical-only classification. Further work should focus on object-level classification and crop monitoring to exploit the rich potential of combined radar and optical observations.

show abstract

Section: Classification Schemesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Synergistic Use of Radar Sentinel-1 and Optical Sentinel-2 Imagery for Crop Mapping: A Case Study for Belgium

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Examples are Global Information and Early Warning System (GIEWS), Famine EarlyWarning Systems NETwork (FEWS NET), MARS crop yield forecasting system (MCYFS), CropWatch, United States Department of Agriculture-Foreign Agricultural Service (USDA-FAS), GEOGLAM, World Food Programme Seasonal Monitor, and Anomaly hot Spots of Agricultural Production (ASAP) [21][22][23][24][25][26]. However, a recent review [26] comparing the aforementioned monitoring systems identifies the lack of ability to operationalize the new methods at a basin level as one of the gaps. These systems provide information at coarser scale meant for global or national assessments, but not always suitable at a basin level monitoring.…”

Section: Introductionmentioning

confidence: 99%

Mapping Agricultural Landuse Patterns from Time Series of Landsat 8 Using Random Forest Based Hierarchial Approach

et al. 2019

View full text Add to dashboard Cite

Increase in irrigated area, driven by demand for more food production, in the semi-arid regions of Asia and Africa is putting pressure on the already strained available water resources. To cope and manage this situation, monitoring spatial and temporal dynamics of the irrigated area land use at basin level is needed to ensure proper allocation of water. Publicly available satellite data at high spatial resolution and advances in remote sensing techniques offer a viable opportunity. In this study, we developed a new approach using time series of Landsat 8 (L8) data and Random Forest (RF) machine learning algorithm by introducing a hierarchical post-processing scheme to extract key Land Use Land Cover (LULC) types. We implemented this approach for Mashhad basin in Iran to develop a LULC map at 15 m spatial resolution with nine classes for the crop year 2015/2016. In addition, five irrigated land use types were extracted for three crop years—2013/2014, 2014/2015, and 2015/2016—using the RF models. The total irrigated area was estimated at 1796.16 km2, 1581.7 km2 and 1578.26 km2 for the cropping years 2013/2014, 2014/2015 and 2015/2016, respectively. The overall accuracy of the final LULC map was 87.2% with a kappa coefficient of 0.85. The methodology was implemented using open data and open source libraries. The ability of the RF models to extract key LULC types at basin level shows the usability of such approaches for operational near real time monitoring.

show abstract

“…The European Commission is also involved in producing various agricultural projections to make crop yield forecasts and crop production estimates, which are necessary at the EU and Member State level to provide the EU's CAP decision makers with timely information for rapid decision-making during the growing season. Estimates of crop production are also useful in relation to trade, development policies and humanitarian assistance linked to food security [4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Projecting investments and fixed assets in agriculture in Latvia

Nipers

Pilvere

Krieviņa

et al. 2019

Engineering for Rural Development

View full text Add to dashboard Cite

To generate projections for agricultural production in Latvia until 2050, the Latvian Agricultural Sector Analysis Model (LASAM) was developed at the Latvia University of Life Sciences and Technologies in 2016. At that stage, the model generated projections for the so-called "activity data", which were used for projecting GHG (greenhouse gases) emissions from agriculture. Nevertheless, the model lacked socio-economic information, including the information on the necessary investment in agriculture and the aggregate value of fixed assets, which could be used for policy analysis and planning, especially within the context of debates about the new European Union (EU) Common Agricultural Policy (CAP) and the Rural Development Plan of Latvia 2021-2027. Within this research, LASAM was extended by a module for the value of fixed assets as at the end of a year and the amount of gross investment required to ensure the achievement of the projected area under crops, the projected number of livestock and the projected total agricultural output in Latvia until 2050. The aim of the research is to produce a projection of aggregate gross investment and of the aggregate value of fixed assets necessary for agriculture in the period until 2050 in Latvia. The research projected gross investments and the value of fixed assets. The authors have concluded that the aggregate gross investment in agriculture in Latvia is expected to increase to EUR 708 mln. in 2030, reaching an aggregate of EUR 1040 mln. in 2050, which are increases of 53 % and 128 %, respectively, compared with 2016, thereby also determining an increase in the aggregate value of fixed assets at the end of the year.

show abstract

A comparison of global agricultural monitoring systems and current gaps

Cited by 210 publications

References 59 publications

Synergistic Use of Radar Sentinel-1 and Optical Sentinel-2 Imagery for Crop Mapping: A Case Study for Belgium

Synergistic Use of Radar Sentinel-1 and Optical Sentinel-2 Imagery for Crop Mapping: A Case Study for Belgium

Mapping Agricultural Landuse Patterns from Time Series of Landsat 8 Using Random Forest Based Hierarchial Approach

Projecting investments and fixed assets in agriculture in Latvia

Contact Info

Product

Resources

About