Pix2pix Conditional Generative Adversarial Network with MLP Loss Function for Cloud Removal in a Cropland Time Series

Clouds are one of the major limitations to crop monitoring using optical satellite images. Despite all efforts to provide decision-makers with high-quality agricultural statistics, there is still a lack of techniques to optimally process satellite image time series in the presence of clouds. In this regard, in this article it was proposed to add a Multi-Layer Perceptron loss function to the pix2pix conditional Generative Adversarial Network (cGAN) objective function. The aim was to enforce the generative model to learn how to deliver synthetic pixels whose values were proxies for the spectral response improving further crop type mapping. Furthermore, it was evaluated the generalization capacity of the generative models in producing pixels with plausible values for images not used in the training. To assess the performance of the proposed approach it was compared real images with synthetic images generated with the proposed approach as well as with the original pix2pix cGAN. The comparative analysis was performed through visual analysis, pixel values analysis, semantic segmentation and similarity metrics. In general, the proposed approach provided slightly better synthetic pixels than the original pix2pix cGAN, removing more noise than the original pix2pix algorithm as well as providing better crop type semantic segmentation; the semantic segmentation of the synthetic image generated with the proposed approach achieved an F1-score of 44.2%, while the real image achieved 44.7%. Regarding the generalization, the models trained utilizing different regions of the same image provided better pixels than models trained using other images in the time series. Besides this, the experiments also showed that the models trained using a pair of images selected every three months along the time series also provided acceptable results on images that do not have cloud-free areas.

A Novel Approach of Ensembling the Transfer Learning Methods for Rice Plant Disease Detection and Classification

Agriculture, the primary sector of Indian economy. It contributes around 18 percent of overall GDP (Gross Domestic Product). More than fifty percent of Indians belong to an agricultural background. There is a necessary to rapidly increase the agriculture production in India due to the vast increasing of population. The significant crop type for most of the people in India is rice but it was one of the crops that has been mostly affected by the cause of diseases in majority of the cases. This results in reduced yield that lead to loss for farmers. The major challenges faced while cultivating the rice crops is getting infected by the diseases due to the various effects that include environmental conditions, pesticides used and natural disasters. Early detection of rice diseases will eventually help farmers to get out from disasters and help in better yield. In this paper, we are proposing a new method of ensembling the transfer learning models to detect the rice plant and classify the diseases using images. Using this model, the three most common rice crop diseases are detected such as Brown spot, Leaf smut and Bacterial leaf blight. Generally, transfer learning uses pre-trained models and gives better accuracy for the image datasets. Also, ensembling of machine learning algorithms (combining two or more ML algorithms) will help in reducing the generalization error and also makes the model more robust. Ensemble learning is becoming trendier as it reduces generalization error as well as makes the model more robust. The ensembling technique that was used in the paper is majority voting. Here we are proposing a novel model that ensembles three transfer learning models which are InceptionV3, MobileNetV2 and DenseNet121 with an accuracy of 96.42%.

Frequency of parasitic infections in Arachishypogaea L (groundnuts), Citrulluslanatus seeds (watermelon seeds), and Ziziphusspina-christi (nabag) sold by street vendors in Khartoum State, Sudan: a cross-sectional study

Background: Plant products, including seeds are an important source of vitamins, minerals, proteins, and energy. This study aimed to assess parasitic contaminations in roasted groundnuts, nabag, and tasali (watermelon seeds) sold by street vendors in Khartoum State, Sudan. Methods: The frequency of parasitic contaminations among all crop products was detected by washing the plants with saline, and then conducting an examination using a formal ether concentration technique (FECT), followed by a saturated sugar floatation technique. Results: The detected parasites belonged to two species: Entamoeba histolytica (33.3%) and Giardia lamblia (15.6%). No helminthic parasites were detected. Mixed contamination of the mentioned parasites was also observed (11.1%). The most contaminated crop was nabag, followed by groundnut, and finally tasali. Conclusion: No relation was established between the positivity of samples for parasites and crop type, Khartoum State city, or seller sex. FECT was more sensitive than the saturated sugar floatation technique as a detection method.

Synergy of Sentinel-1 and Sentinel-2 Imagery for Early Seasonal Agricultural Crop Mapping

The exploitation of the unprecedented capacity of Sentinel-1 (S1) and Sentinel-2 (S2) data offers new opportunities for crop mapping. In the framework of the SenSAgri project, this work studies the synergy of very high-resolution Sentinel time series to produce accurate early seasonal binary cropland mask and crop type map products. A crop classification processing chain is proposed to address the following: (1) high dimensionality challenges arising from the explosive growth in available satellite observations and (2) the scarcity of training data. The two-fold methodology is based on an S1-S2 classification system combining the so-called soft output predictions of two individually trained classifiers. The performances of the SenSAgri processing chain were assessed over three European test sites characterized by different agricultural systems. A large number of highly diverse and independent data sets were used for validation experiments. The agreement between independent classification algorithms of the Sentinel data was confirmed through different experiments. The presented results assess the interest of decision-level fusion strategies, such as the product of experts. Accurate crop map products were obtained over different countries in the early season with limited training data. The results highlight the benefit of fusion for early crop mapping and the interest of detecting cropland areas before the identification of crop types.

Quantifying the nutritional and income loss due to crop raiding in rural African subsistence farming community in South Africa

Globally, crop damage by wildlife contributes to food insecurity through direct loss of food and income. We investigated the calories lost and potential economic impact of crop raiding to subsistence homesteads abutting the Hluhluwe Game Reserve and assessed their mitigation measures to combat crop raiding. We quantified the seasonal loss of calories (KJ/g) of four common crops: beetroot (Beta vulgaris), common bean (Phaseolus vulgaris), maize (Zea mays) and spinach (Spinacia oleracea) and determined seasonal potential income loss based on local market cost of crops. Experimental data used for this study were collected from April 2016-March 2017 and questionnaire data were collected in March 2016, using a stratified sampling approach to sample the homesteads. We selected every second homestead for the interview and restricted the survey to one respondent per homestead to avoid pseudo-replication of results. In the one year of sampling, we did not record any large mammals crop raiding, both from direct observations and camera trap footage, we also did not find a statistically significant relationship between the level of damage and distance of farms from the reserve boundary. Throughout the study, we captured a total of 96 individual rodents comprising of two species: red bush rat (Aethomys spp.; 67.7%; 51 males and 28 females) and pouched mouse (Saccostomus campestris; 32.3% (14 females and three males ) and we used the damage caused by these animals and other small animals to quantify the level of damage. We found that season, crop type, farm slope and the interaction between season and crop type were significant predictors of relative calorie loss. Again, season, crop type and the interaction between season and crop type were significant predictors of the potential income loss, with the highest income loss recorded for spinach in the dry season. In addition, significant differences were found for potential income loss for all crop types in the wet season, and for the interaction between crop types maize, spinach and the wet season, but no significant difference was found for crop type common bean and the wet season. A multinomial regression analysis revealed that crop raiding animal type, crop types raided and distance of farms from the reserve all had a significant effect on the choice of mitigation measures farmers used. Most importantly we found the highest relative calorie loss for maize during the dry season, which could impact on subsistence farmers by reducing their daily calorie intake and impact on their food security especially during the season where subsistence farming is slow. Moreover, as the most preferred mitigation measure by farmers can have opportunity costs to this community, such as the loss of school time for children. These results have important implications for food security policies and socially related policies and practices.

Frequency of parasitic infections in Arachishypogaea L (groundnuts), Citrulluslanatus seeds (watermelon seeds), and Ziziphusspina-christi (nabag) sold by street vendors in Khartoum State, Sudan: a cross-sectional study

Background: Plant products, including seeds are an important source of vitamins, minerals, proteins, and energy. This study aimed to assess parasitic contaminations in roasted groundnuts, nabag, and tasali (watermelon seeds) sold by street vendors in Khartoum State, Sudan. Methods: The frequency of parasitic contaminations among all crop products was detected by washing the plants with saline, and then conducting an examination using a formal ether concentration technique (FECT), followed by a saturated sugar floatation technique. Results: The detected parasites belonged to two species: Entamoeba histolytica (33.3%) and Giardia lamblia (15.6%). No helminthic parasites were detected. Mixed contamination of the mentioned parasites was also observed (11.1%). The most contaminated crop was nabag, followed by groundnut, and finally tasali. Conclusion: No relation was established between the positivity of samples for parasites and crop type, Khartoum State city, or seller sex. FECT was more sensitive than the saturated sugar floatation technique as a detection method.

Contrasting yield responses at varying levels of shade suggest different suitability of crops for dual land-use systems. A meta-analysis.

Despite the large body of research studying crop growth parameters, there is still a lack of systematic assessments on how harvestable yields of different crop types respond to varying levels of shading. However, with the advent of agrivoltaic (AV) systems, a technology that combines energy and food production, and the new focus on agroforestry (AF), shade tolerance is becoming an important parameter for crop production systems. To address this research gap, a meta-analysis with data from two experimental approaches (intercropping and artificial shading with cloths, nets or solar panels) was performed to quantitatively assess the susceptibility of different temperate crop types to increasing levels of shading. Crop type specific yield response curves were estimated as a function of reduction in solar radiation (RSR), by estimating relative crop yields compared to the unshaded controls. Only studies that reported RSR and crop yield per area in temperate and subtropical areas were included. Using a random slope effect for each study, the specific variance components were accounted for. The results suggested a nonlinear relationship between achieved crop yields and RSR for all crop types. Most crops tolerate RSR up to 15%, showing a less than proportionate yield decline. However, significant differences between the response curves of different crop types existed: Berries, fruits and fruity vegetables benefited from shading up to RSR of 30%. Forages, leafy vegetables, tubers/root crops and C3 cereals showed initially less than proportionate crop yield loss. In contrast, maize and grain legumes experienced strong crop yield losses even at low RSR levels. The results provide first indicators for differences in crop type suitability to shading, and thus for AV and AF systems. Detailed yield response curves, as provided in this study, are valuable tools to optimize the output of annual crop components in AV and AF systems.