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.
By monitoring crops through machine learning and satellite data, Stanford scientists have found farms that till the soil less can increase yields of corn and soybeans and improve the health of the soil – a win-win for meeting growing food needs worldwide.
Agriculture degrades over 24 million acres of fertile soil every year, raising concerns about meeting the rising global demand for food. But a simple farming practice born from the 1930’s Dust Bowl could provide a solution, according to new Stanford research. The study, published Dec. 6 in Environmental Research Letters, shows that Midwest farmers who reduced how much they overturned the soil – known as tilling – increased corn and soybean yields while also nurturing healthier soils and lowering production costs.
“Reduced tillage is a win-win for agriculture across the Corn Belt,” said study lead author Jillian Deines, a postdoctoral scholar at Stanford’s Center on Food Security and the Environment. “Worries that it can hurt crop yields have prevented some farmers from switching practices, but we found it typically leads to increased yields.”
The U.S. – the largest producer of corn and soybeans worldwide – grows a majority of these two crops in the Midwest. Farmers plucked about 367 million metric tons of corn and 108 million metric tons of soybeans from American soil this past growing season, providing key food, oil, feedstock, ethanol and export value.
Monitoring farming from space
Farmers generally till the soil prior to planting corn or soybeans – a practice known to control weeds, mix nutrients, break up compacted dirt and ultimately increase food production over the short term. However, over time this method degrades soil. A 2015 report from the Food and Agriculture Organization of the United Nations found that in the past 40 years the world has lost a third of food-producing land to diminished soil. The demise of once fertile land poses a serious challenge for food production, especially with mounting pressures on agriculture to feed a growing global population.
In contrast, reduced tillage – also known as conservation tillage – promotes healthier soil management, reduces erosion and runoff and improves water retention and drainage. It involves leaving the previous year’s crop residue (such as corn stalks) on the ground when planting the next crop, with little or no mechanical tillage. The practice is used globally on over 370 million acres, mostly in South America, Oceania and North America. However, many farmers fear the method could reduce yields and profits. Past studies of yield effects have been limited to local experiments, often at research stations, that don’t fully reflect production-scale practices.
The Stanford team turned to machine learning and satellite datasets to address this knowledge gap. First, they identified areas of reduced and conventional tilling from previously published data outlining annual U.S. practices for 2005 to 2016. Using satellite-based crop yield models – which take into account variables such as climate and crop life-cycles – they also reviewed corn and soybean yields during this time. To quantify the impact of reduced tillage on crop yields, the researchers trained a comput
er model to compare changes in yields based on tillage practice. They also recorded elements such as soil type and weather to help determine which conditions had a larger influence on harvests.
The researchers calculated corn yields improved an average of 3.3 percent and soybeans by 0.74 percent across fields managed with long-term conservation tillage practices in the nine states sampled. Yields from the additional tonnage rank in the top 15 worldwide for both crops. For corn, this totals approximately 11 million additional metric tons matching the 2018 country output of South Africa, Indonesia, Russia or Nigeria. For soybeans, the added 800,000 metric tons ranks in between Indonesia and South Africa’s country totals.
Some areas experienced up to an 8.1 percent increase for corn and 5.8 percent for soybeans. In other fields, negative yields of 1.3 percent for corn and 4.7 for soybeans occurred. Water within the soil and seasonal temperatures were the most influential factors in yield differences, especially in drier, warmer regions. Wet conditions were also found favorable to crops except during the early season where water-logged soils benefit from conventional tillage that in turn dries and aerates.
“Figuring out when and where reduced tillage works best could help maximize the benefits of the technology and guide farmers into the future,” said study senior author David Lobell, a professor of Earth system science in the School of Earth, Energy & Environmental Sciences and the Gloria and Richard Kushel Director of the Center on Food Security and the Environment.
It takes time to see the benefits from reduced tillage, as it works best under continuous implementation. According to the researchers’ calculations, corn farmers won’t see the full benefits for the first 11 years, and soybeans take twice as long for full yields to materialize. However, the approach also results in lower costs due to reduced need for labor, fuel and farming equipment while also sustaining fertile lands for continuous food production. The study does show a small positive gain even during the first year of implementation, with higher gains accruing over time as soil health improves. According to a 2017 Agricultural Censuses report, farmers appear to be getting on board with the long-term investment and close to 35 percent of cropland in the U.S. is now managed with reduced tillage.
“One of the big challenges in agriculture is achieving the best crop yields today without comprising future production. This research demonstrates that reduced tillage can be a solution for long-term crop productivity,” Deines said.
David Lobell is also the William Wrigley Senior Fellow at the Stanford Woods Institute for the Environment, a senior fellow at the Freeman Spogli Institute for International Studies and the Stanford Institute for Economic Policy and Research. Graduate student Sherrie Wang is also a co-author. Research was funded by NASA Harvest.
Accurate prediction of crop yields in developing countries in advance of harvest time is central to preventing famine, improving food security, and sustainable development of agriculture. Existing techniques are expensive and difficult to scale as they require locally collected survey data. Approaches utilizing remotely sensed data, such as satellite imagery, potentially provide a cheap, equally effective alternative. Our work shows promising results in predicting soybean crop yields in Argentina using deep learning techniques. We also achieve satisfactory results with a transfer learning approach to predict Brazil soybean harvests with a smaller amount of data. The motivation for transfer learning is that the success of deep learning models is largely dependent on abundant ground truth training data. Successful crop yield prediction with deep learning in regions with little training data relies on the ability to fine-tune pre-trained models.
All Publications button
COMPASS '18 Proceedings of the 1st ACM SIGCAS Conference on Computing and Sustainable Societies
Nicole Kravec, Stanford Center for Ocean Solutions
Stanford’s Center for Ocean Solutions and Center on Food Security and the Environment, together with Springer-Nature, are hosting a workshop focused on building a research agenda that, for the first time, analyzes the role of oceans within the context of global food systems.
Massive changes in the global food sector over the next few decades – driven by climate change and other environmental stresses, growing population and income, advances in technology, and shifts in policies and trade patterns – will have profound implications for the oceans and vice versa. While there is a large community of researchers addressing challenges in food policy and agriculture and a similar community in oceans and fisheries, there is very little interaction between them. This workshop addresses a pressing need to foster more interaction among these communities, to build a research agenda that illuminates the many interconnections among food and the oceans, and to inform action to meet these challenges.
“Stanford is in a perfect position to take the lead in developing this new area of research and outreach, with its strong expertise in terrestrial food systems, global food security, and the oceans,” claims Roz Naylor, Professor of Earth System Science, founding Director of the Center on Food Security and the Environment, and co-organizer of the workshop.
This event brings together diverse leaders across academia, business, policy, and government. Together participants will analyze the role of the oceans within a global food systems context, highlighting issues related to food security, equity, poverty alleviation, marine ecosystems, and environmental change. The aim is to define and develop this emerging field, as researchers and stakeholders explore cutting edge ideas and identify emerging trends and challenges that can inform ongoing policy discussions.
“This is a unique opportunity to build a new and vibrant community, bringing together leading researchers in oceans, fisheries, food, and agriculture from around the world," explained COS co-director Jim Leape. "We're coming together to ask the key questions needed to identify emerging themes and solutions, in lockstep with those who will put these findings into practice," added COS co-director Fiorenza Micheli. "As the world's demand for food continues to grow, we will increasingly need to understand and act on the critical role of the oceans to meet these challenges."
Jim Leape is also the William and Eva Price Fellow at the Stanford Woods Institute for the Environment. Fiorenza Micheli is also the David and Lucile Packard Professor in Marine Sciences at Stanford's Hopkins Marine Station and senior fellow at the Woods Institute. Read more about the Stanford Center for Ocean Solutions.
Our Report draws attention to a complex but understudied issue: How will climate warming alter losses of major food crops to insect pests? Because empirical evidence on plant-insect-climate interactions is scarce and geographically localized, we developed a physiologically based model that incorporates strong and well-established effects of temperature on metabolic rates and on population growth rates. We acknowledged that other factors are involved, but the ones we analyzed are general, robust, and global (1–3).
Parmesan and colleagues argue that our model is overly simplistic and that any general model is premature. They are concerned that our model does not incorporate admittedly idiosyncratic and geographically localized aspects of plant-insect interactions. Some local effects, such as evidence that warmer winters will harm some insects but not others, were in fact evaluated in our sensitivity analyses and shown to be minor (see the Report's Supplementary Materials). Other phenomena, such as plant defenses that benefit some insects and threaten others, are relevant but are neither global nor directional. Furthermore, because Parmesan et al. present no evidence that such idiosyncratic and localized interactions will outweigh the cardinal and universally strong impacts of temperature on populations and on metabolic rates (1–3), their conclusion is subjective.
We agree with Parmesan and colleagues that the question of future crop losses is important and needs further study, that targeted experimental data are needed (as we wrote in our Report), and that our estimates are likely to be conservative (as we concluded, but for reasons different from theirs). However, we strongly disagree with their recommendation to give research priority to gathering localized experimental data. That strategy will only induce a substantial time lag before future crop losses can be addressed.
We draw a lesson from models projecting future climates. Those models lack the “complexity and idiosyncratic nature” of many climate processes, but by building from a few robust principles, they successfully capture the essence of climate patterns and trends (4). Similarly, we hold that the most expeditious and effective way to anticipate crop losses is to develop well-evidenced ecological models and use them to help guide targeted experimental approaches, which can subsequently guide revised ecological models. Experiments and models should be complementary, not sequential.
All Publications button
Curtis A. Deutsch, Joshua J. Tewksbury, Michelle Tigchelaar, David S. Battisti, Scott C. Merrill, Raymond B. Huey
Reconciling higher freshwater demands with finite freshwater resources remains one of the great policy dilemmas. Given that crop irrigation constitutes 70% of global water extractions, which contributes up to 40% of globally available calories (1), governments often support increases in irrigation efficiency (IE), promoting advanced technologies to improve the “crop per drop.” This provides private benefits to irrigators and is justified, in part, on the premise that increases in IE “save” water for reallocation to other sectors, including cities and the environment. Yet substantial scientific evidence (2) has long shown that increased IE rarely delivers the presumed public-good benefits of increased water availability. Decision-makers typically have not known or understood the importance of basin-scale water accounting or of the behavioral responses of irrigators to subsidies to increase IE. We show that to mitigate global water scarcity, increases in IE must be accompanied by robust water accounting and measurements, a cap on extractions, an assessment of uncertainties, the valuation of trade-offs, and a better understanding of the incentives and behavior of irrigators.
All Publications button
J. Williams, C. J. Perry, F. Molle, C. Ringler, P. Steduto, B. Udall, S. A. Wheeler, Y. Wang, D. Garrick, R. G. Allen
Low-intensity tillage has become more popular among farmers in the United States and many other regions. However, accurate data on when and where low-intensity tillage methods are being used remain scarce, and this scarcity impedes understanding of the factors affecting the adoption and the agronomic or environmental impacts of these practices. In this study, we used composites of satellite imagery from Landsat 5, 7, and 8, and Sentinel-1 in combination with producer data from about 5900 georeferenced fields to train a random forest classifier and generate annual large-scale maps of tillage intensity from 2005 to 2016. We tested different combinations of hyper-parameters using cross-validation, splitting the training and testing data alternatively by field, year, and state to assess the influence of clustering on validation results and evaluate the generalizability of the classification model. We found that the best model was able to map tillage practices across the entire North Central US region at 30 m-resolution with accuracies spanning between 75% and 79%, depending on the validation approach. We also found that although Sentinel-1 provides an independent measure that should be sensitive to surface moisture and roughness, it currently adds relatively little to classification performance beyond what is possible with Landsat. When aggregated to the state level, the satellite estimates of percentage low- and high-intensity tillage agreed well with a USDA survey on tillage practices in 2006 (R2 = 0.55). The satellite data also revealed clear increases in low-intensity tillage area for most counties in the past decade. Overall, the ability to accurately map spatial and temporal patterns in tillage should facilitate further study of this important practice in the United States, as well as other regions with fewer survey-based estimates.
All Publications button
Remote Sensing of Environment
Patricio Grassini, Juan Ignaci, Rattalino Edreira, Shawn Conley, Spyridon Mourtzinis
Professor Gorelick runs the Hydrogeology and Water Resources program and directs the interdisciplinary Global Freshwater Initiative. He is also a Senior Fellow at the Woods Institute for the Environment. Dr. Gorelick is a US National Academy of Engineering (NAE) member and received Fulbright and Guggenheim Fellowships for research on water and oil resources. He is a Fellow of the American Association for the Advancement of Science (AAAS), American Geophysical Union (AGU) and the Geological Society of America (GSA. Dr. Gorelick has produced over 140 journal papers and 3 books in the areas of water management in underdeveloped regions, hydrogeology, optimal remediation design, hydrogeophysics, ecohydrology, and global oil resources.
Dr. Noah Diffenbaugh is the Kara J Foundation Professor and Kimmelman Family Senior Fellow at Stanford University. He studies the climate system, including the processes by which climate change could impact agriculture, water resources, and human health. Dr. Diffenbaugh is currently Editor-in-Chief of the peer-review journal Geophysical Research Letters. He has served as a Lead Author for Working Group II of the Intergovernmental Panel on Climate Change (IPCC), and has provided testimony and scientific expertise to the White House, the Governor of California, and U.S. Congressional offices. Dr. Diffenbaugh is a recipient of the James R. Holton Award from the American Geophysical Union, a CAREER award from the National Science Foundation, and a Terman Fellowship from Stanford University. He has also been recognized as a Kavli Fellow by the U.S. National Academy of Sciences, and as a Google Science Communication Fellow.
Increased intake of fruits and vegetables (F&V) is recommended for most populations across the globe. However, the current state of global and regional food systems is such that F&V availability, the production required to sustain them, and consumer food choices are all severely deficient to meet this need. Given the critical state of public health and nutrition worldwide, as well as the fragility of the ecological systems and resources on which they rely, there is a great need for research, investment, and innovation in F&V systems to nourish our global population. Here, we review the challenges that must be addressed in order to expand production and consumption of F&V sustainably and on a global scale. At the conclusion of the workshop, the gathered participants drafted the “Aspen/Keystone Declaration” (see below), which announces the formation of a new “Community of Practice,” whose area of work is described in this position paper. The need for this work is based on a series of premises discussed in detail at the workshop and summarized herein. To surmount these challenges, opportunities are presented for growth and innovation in F&V food systems. The paper is organized into five sections based on primary points of intervention in global F&V systems: (1) research and development, (2) information needs to better inform policy & investment, (3) production (farmers, farming practices, and supply), (4) consumption (availability, access, and demand), and (5) sustainable & equitable F&V food systems and supply chains.