Accurate automated segmentation of remote sensing data could benefit applications from land cover mapping and agricultural monitoring to urban development surveyal and disaster damage assessment. While convolutional neural networks (CNNs) achieve state-of-the-art accuracy when segmenting natural images with huge labeled datasets, their successful translation to remote sensing tasks has been limited by low quantities of ground truth labels, especially fully segmented ones, in the remote sensing domain. In this work, we perform cropland segmentation using two types of labels commonly found in remote sensing datasets that can be considered sources of “weak supervision”: (1) labels comprised of single geotagged points and (2) image-level labels. We demonstrate that (1) a U-Net trained on a single labeled pixel per image and (2) a U-Net image classifier transferred to segmentation can outperform pixel-level algorithms such as logistic regression, support vector machine, and random forest. While the high performance of neural networks is well-established for large datasets, our experiments indicate that U-Nets trained on weak labels outperform baseline methods with as few as 100 labels. Neural networks, therefore, can combine superior classification performance with efficient label usage, and allow pixel-level labels to be obtained from image labels.

The economic costs of Indonesia’s 2015 forest fires are estimated to exceed US $16 billion, with more than 100,000 premature deaths. On several days the fires emitted more carbon dioxide than the entire United States economy. Here, we combine detailed geospatial data on fire and local climatic conditions with rich administrative data to assess the underlying causes of Indonesia’s forest fires at district and village scales. We find that El Niño events explain most of the year-on-year variation in fire. The creation of new districts increases fire and exacerbates the El Niño impacts on fire. We also find that regional economic growth has gone hand-in-hand with the use of fire in rural districts. We proceed with a 30,000-village case study of the 2015 fire season on Sumatra and Kalimantan and ask which villages, for a given level of spatial fire risk, are more likely to have fire. Villages more likely to burn tend to be more remote, to be considerably less developed, and to have a history of using fire for agriculture. Although central and district level policies and regional economic development have generally contributed to voracious environmental degradation, the close link between poverty and fire at the village level suggests that the current policy push for village development might offer opportunities to reverse this trend.

Eradicating hunger and malnutrition is a key development goal of the twenty first century. This paper addresses the problem of optimally identifying seed varieties to reliably increase crop yield within a risk-sensitive decision making framework. Specifically, a novel hierarchical machine learning mechanism for predicting crop yield (the yield of different seed varieties of the same crop) is introduced. This prediction mechanism is then integrated with a weather forecasting model and three different approaches for decision making under uncertainty to select seed varieties for planting so as to balance yield maximization and risk. The model was applied to the problem of soybean variety selection given in the 2016 Syngenta Crop Challenge. The prediction model achieved a median absolute error of 235 kg/ha and thus provides good estimates for input into the decision models. The decision models identified the selection of soybean varieties that appropriately balance yield and risk as a function of the farmer’s risk aversion level. More generally, the models can support farmers in decision making about which seed varieties to plant.

This publication summarizes the agricultural policy analyses conducted in nine Caribbean countries (Suriname, Guyana, Haiti, Dominican Republic, Jamaica, Belize, Barbados, The Bahamas, and Trinidad and Tobago) in the framework of the IDB’s Agrimonitor initiative. The document discusses how agricultural policies affect producers and consumers as well as how the limited funding for agricultural services, such as research and infrastructure, could limit the ability of Caribbean farmers to compete effectively in global markets. The analyses presented are therefore meant to contribute to the Caribbean’s regional dialogue for the design of more effective agricultural policies, which will be able to strengthen the sector and improve the lives of people in the region.

Abstract: The goal of the present paper is to examine how the expansion of the economy from 2000 has affected rural off-farm labor market participation. Specifically, we seek to determine whether off-farm labor increased after 2000, what forms of employment are driving trends in off-farm labor and whether gender differences can be observed in off farm employment trends. Using a nationally representative dataset that consist of two waves of surveys conducted in 2000 and 2008 in six provinces, this paper finds that off farm labor market participation continued to rise steadily in the early 2000s. However, there is a clear difference in the trends associated with occupational choice before and after 2000. In addition, we find that rural off-farm employment trends are different for men and women. Our analysis also shows that the rise of wage-earning employment corresponds with an increasing unskilled wage for both men and women.

Large and regular seasonal price fluctuations in local grain markets appear to offer African farmers substantial inter-temporal arbitrage opportunities, but these opportunities remain largely unexploited: small-scale farmers are commonly observed to "sell low and buy high" rather than the reverse. In a field experiment in Kenya, we show that credit market imperfections limit farmers' abilities to move grain inter-temporally. Providing timely access to credit allows farmers to buy at lower prices and sell at higher prices, increasing farm revenues and generating a return on investment of 28%. To understand general equilibrium effects of these changes in behavior, we vary the density of loan offers across locations. We document significant effects of the credit intervention on seasonal price fluctuations in local grain markets, and show that these GE effects shape individual level profitability estimates. In contrast to existing experimental work, the results indicate a setting in which microcredit can improve firm profitability, and suggest that GE effects can substantially shape microcredit's effectiveness. In particular, failure to consider these GE effects could lead to underestimates of the social welfare benefits of microcredit interventions.

A critical question for agricultural production and food security is how water demand for staple crops will respond to climate and carbon dioxide (CO2) changes1, especially in light of the expected increases in extreme heat exposure2. To quantify the trade-offs between the effects of climate and CO2 on water demand, we use a ‘sink-strength’ model of demand3,4 which relies on the vapour-pressure deficit (VPD), incident radiation and the efficiencies of canopy-radiation use and canopy transpiration; the latter two are both dependent on CO2. This model is applied to a global data set of gridded monthly weather data over the cropping regions of maize, soybean, wheat and rice during the years 1948–2013. We find that this approach agrees well with Penman–Monteith potential evapotranspiration (PM) for the C3 crops of soybean, wheat and rice, where the competing CO2 effects largely cancel each other out, but that water demand in maize is significantly overstated by a demand measure that does not include CO2, such as the PM. We find the largest changes in wheat, for which water demand has increased since 1981 over 86% of the global cropping area and by 2.3–3.6 percentage points per decade in different regions.

Policies that promote biofuels in major agricultural economies raise important questions for food prices and food security at local to global scales. Global biofuel output rose from 38 billion liters to 131 billion liters between 2005 and 2015, boosting the demand for annual- and perennial-crop feedstocks such as maize, sugar, soy, rapeseed, and palm oil. Although ethanol volume was three times that of biodiesel in 2015, the share of biodiesel in total biofuel output rose from 10% to almost 25% over the course of the decade (EIA, n.d.; REN21, 2016). Biodiesel production increased 700% between 2005 and 2015 and is expected to rise by another 35% by 2025 (OECD/FAO, 2014). In this paper, we examine the linkages between biodiesel, oil crop, and energy markets, and ask: What are the food security implications of biodiesel policies in major agricultural economies? How do governments adjust biodiesel policies in response to international commodity prices, trade opportunities, and their changing economic and environmental priorities?