High food demand has led stakeholders to regularly monitor agricultural production to ensure food security and a balanced ecosystem. Agricultural areas undergo rapid changes throughout a growing season due to phenology. Crop mapping initiatives therefore require efficient and effective information gathering techniques. Remote sensing, specifically radar, offers an effective land-cover mapping platform compared to ground surveying methods. Radar is sensitive to crop physical structure and biomass/vegetation water content, i.e. dielectric property. We adopt and test the potential of the recent Sentinel 1 images for multitemporal crop classification due to its short revisit period and sufficient spatial resolution. The temporal resolution guarantees the highest temporal density of images that captures crop dynamics. However, this presents dimensionality problems in classification algorithms. Therefore, we chose dynamic conditional random fields (DCRFs) and tested their robustness in high-dimensional images constrained to few training data. DCRFs are designed to incorporate spatio-temporal phenological information inherent in images during crop classification. We compare the approach to single epoch classification. Our findings indicate that DCRFs improved crop mapping accuracy in all epochs. Nonetheless, most stakeholders require seasonal crop-type statistics. Hence, we use an ensemble classifier to produce an optimal map from posterior class probabilities estimated from the sequence of images. The ensemble outperforms the conventional approach of merging multitemporal images as composite bands for classification using Maximum Likelihood Classifier (MLC-stack) and mono-temporal conditional random fields. It still retains high accuracy compared to MLC-stack when subjected to high-dimensional images with fewer training data.

The rising food demand requires regular agriculture land-cover updates to support food security initiatives. Agricultural areas undergo dynamic changes throughout the year, which manifest varying radar backscatter due to crop phenology. Certain crops can show similar backscatter if their phenology intersects, but vary later when their phenology differs. Hence, classification techniques based on single-date remote sensing images may not offer optimal results for crops with similar phenology. Moreover, methods that stack images within a cropping season as composite bands for classification limit discrimination to one feature space vector, which can suffer from overlapping classes. Nonetheless, phenology can aid classification of crops, because their backscatter varies with time. This paper fills this gap by introducing a crop sequence-based ensemble classification method where expert knowledge and TerraSAR-X multitemporal image-based phenological information are explored. We designed first-order and higher order dynamic conditional random fields (DCRFs) including an ensemble technique. The DCRF models have a duplicated structure of temporally connected CRFs, which encode image-based phenology and expert-based phenology knowledge during classification. On the other hand, our ensemble generates an optimal map based on class posterior probabilities estimated by DCRFs. These techniques improved crop delineation at each epoch, with higher order DCRFs (HDCRFs) giving the best accuracy. The ensemble method was evaluated against the conventional technique of stacking multitemporal images as composite bands for classification using maximum likelihood classifier (MLC) and CRFs. It surpassed MLC and CRFs based on class posterior probabilities estimated by both first-order DCRFs and HDCRFs.

Agricultural index insurance contracts increasingly use remote sensing data to estimate losses and determine indemnity payouts. Index insurance contracts inevitably make errors, failing to detect losses that occur and issuing payments when no losses occur. The quality of these contracts and the indices on which they are based, need to be evaluated to assess their fitness as insurance, and to provide a guide to choosing the index that best protects the insured. In the remote sensing literature, indices are often evaluated with generic model evaluation statistics such as R² or Root Mean Square Error that do not directly consider the effect of errors on the quality of the insurance contract. Economic analysis suggests using measures that capture the impact of insurance on the expected economic well-being of the insured. To bridge the gap between the remote sensing and economic perspectives, we adopt a standard economic measure of expected well-being and transform it into a Relative Insurance Benefit (RIB) metric. RIB expresses the welfare benefits derived from an index insurance contract relative to a hypothetical contract that perfectly measures losses. RIB takes on its maximal value of one when the index contract offers the same economic benefits as the perfect contract. When it achieves none of the benefits of insurance it takes on a value of zero, and becomes negative if the contract leaves the insured worse off than having no insurance. Part of our contribution is to decompose this economic well-being measure into an asymmetric loss function. We also argue that the expected well-being measure we use has advantages over other economic measures for the normative purpose of insurance quality ascertainment. Finally, we illustrate the use of the RIB measure with a case study of potential livestock insurance contracts in Northern Kenya. We compared 24 indices that were made with 4 different statistical models and 3 remote sensing data sources. RIB for these indices ranged from 0.09 to 0.5, and R² ranged from 0.2 to 0.51. While RIB and R² were correlated, the model with the highest RIB did not have the highest R². Our findings suggest that, when designing and evaluating an index insurance program, it is useful to separately consider the quality of a remote sensing-based index with a metric like the RIB instead of a generic goodness-of-fit metric.